© 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. 19-RESID-POST-AA
    11. 72087
    Prev
    Next
    INDEX
    Explanations

    Locale settings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    你们
    -0.07
    power
    -0.07
     notícia
    -0.07
     University
    -0.07
    queued
    -0.07
     untuk
    -0.07
     Produce
    -0.07
     России
    -0.06
     document
    -0.06
     cherche
    -0.06
    POSITIVE LOGITS
    always
    0.07
    -am
    0.07
    GD
    0.07
     elementary
    0.07
    .habbo
    0.07
    .snap
    0.07
     afterward
    0.07
    ()"↵
    0.07
    是否会
    0.06
    -Ass
    0.06
    Activations Density 0.001%

    No Known Activations