© 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. 7-RESID-POST-AA
    11. 6767
    Prev
    Next
    INDEX
    Explanations

    execution

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Ώ
    -0.07
     underage
    -0.07
     Nullable
    -0.07
    ihil
    -0.07
    运势
    -0.07
    opsy
    -0.06
    𫫇
    -0.06
    魇
    -0.06
    pir
    -0.06
     grupo
    -0.06
    POSITIVE LOGITS
    $con
    0.08
    _TO
    0.07
     gras
    0.07
    おか
    0.07
     ス
    0.07
    麦克
    0.07
    \">\
    0.07
    ಸ
    0.06
    став
    0.06
     tenth
    0.06
    Activations Density 0.014%

    No Known Activations