© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 5627
    Prev
    Next
    INDEX
    Explanations

    tip

    np_max-act · gemini-2.0-flash

    calls to action inviting the public to report information or submit anonymous tips to authorities via hotlines, tip lines, or online submission systems, often with contact details.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    쌩
    -0.08
    oti
    -0.07
     mio
    -0.07
    twor
    -0.07
    explicit
    -0.07
    トラ
    -0.07
     deuxième
    -0.07
    咱
    -0.06
     noch
    -0.06
     또
    -0.06
    POSITIVE LOGITS
     Fat
    0.07
    mates
    0.07
    Cancelar
    0.07
     средне
    0.07
    _sleep
    0.07
    sehen
    0.07
     superv
    0.07
    <Role
    0.07
    组成的
    0.07
     impaired
    0.06
    Activations Density 0.076%

    No Known Activations