© 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. 71821
    Prev
    Next
    INDEX
    Explanations

    Sleeves

    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
    ตลอด
    -0.07
    ありますが
    -0.07
    まま
    -0.07
    .Virtual
    -0.07
    =ax
    -0.07
     enrichment
    -0.07
    Scalars
    -0.07
    scrollTop
    -0.07
    iox
    -0.07
     smb
    -0.07
    POSITIVE LOGITS
     escalating
    0.07
    老太太
    0.06
    /pre
    0.06
    نت
    0.06
    电子产品
    0.06
     prostitutes
    0.06
     Applying
    0.06
    _cliente
    0.06
     populations
    0.06
     recalled
    0.06
    Activations Density 0.010%

    No Known Activations