© 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. 94410
    Prev
    Next
    INDEX
    Explanations

    say "android or xmlns"

    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
    单纯的
    -0.07
    ắc
    -0.07
    传球
    -0.07
     buffet
    -0.07
     ICommand
    -0.07
     productions
    -0.07
     Wage
    -0.07
    Ɯ
    -0.07
     vuel
    -0.06
    hänge
    -0.06
    POSITIVE LOGITS
    !="
    0.07
     Often
    0.07
    行政处罚
    0.07
    的感觉
    0.07
    监测
    0.06
    च
    0.06
    UnitOfWork
    0.06
    ≥
    0.06
    প
    0.06
    ক
    0.06
    Activations Density 0.004%

    No Known Activations