© 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. 79250
    Prev
    Next
    INDEX
    Explanations

    knitting

    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
    Negative Logits
    有幸
    -0.08
    挞
    -0.08
    Dave
    -0.07
     sez
    -0.07
    长长的
    -0.07
    市委常委
    -0.07
    meye
    -0.07
     tissues
    -0.06
     Flour
    -0.06
    Steam
    -0.06
    POSITIVE LOGITS
    ibrary
    0.08
    jm
    0.07
    grammar
    0.07
    ༊
    0.07
    *l
    0.07
    ям
    0.06
     Despite
    0.06
    уществ
    0.06
    eco
    0.06
     gameState
    0.06
    Activations Density 0.003%

    No Known Activations