© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 84451
    Prev
    Next
    INDEX
    Explanations

    indices and code

    np_max-act · gemini-2.0-flash
    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
    长达
    -0.07
    _BUF
    -0.07
    TL
    -0.07
    Bah
    -0.07
    ń
    -0.06
     legitimately
    -0.06
     populated
    -0.06
     legitimate
    -0.06
    $result
    -0.06
    迄今为止
    -0.06
    POSITIVE LOGITS
    上海证券
    0.07
     мож
    0.07
    measure
    0.07
     fChain
    0.07
    龁
    0.07
    惛
    0.07
    _clear
    0.06
    tparam
    0.06
    俦
    0.06
     scandal
    0.06
    Activations Density 0.030%

    No Known Activations