© 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. 15-RESID-POST-AA
    11. 70039
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     isset
    -0.08
    .Packet
    -0.07
     mennes
    -0.07
     Terra
    -0.07
     piece
    -0.07
    (xml
    -0.07
    此项
    -0.06
    /my
    -0.06
    (Room
    -0.06
     missing
    -0.06
    POSITIVE LOGITS
    解放
    0.09
     kids
    0.07
    🐬
    0.07
    互助
    0.07
    羖
    0.07
    ständ
    0.07
     ücrets
    0.07
     dream
    0.07
    娣
    0.07
    厄
    0.07
    Activations Density 0.003%

    No Known Activations