© 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. 71878
    Prev
    Next
    INDEX
    Explanations

    [

    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
     arose
    -0.07
    sect
    -0.07
     asylum
    -0.06
    dí
    -0.06
    (curl
    -0.06
    营地
    -0.06
    onde
    -0.06
     extremism
    -0.06
    ls
    -0.06
    .destination
    -0.06
    POSITIVE LOGITS
    ERVICE
    0.07
     vs
    0.07
     Leakage
    0.07
    }{↵
    0.07
     listItem
    0.07
    的人都
    0.07
    >N
    0.06
     prefixed
    0.06
    ()):↵
    0.06
    TRY
    0.06
    Activations Density 0.008%

    No Known Activations