© 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. 29406
    Prev
    Next
    INDEX
    Explanations

    document excerpts

    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
    (link
    -0.07
    (master
    -0.07
    ق
    -0.07
    civil
    -0.07
    â
    -0.07
    cks
    -0.06
    白衣
    -0.06
    ï
    -0.06
    株
    -0.06
    矛
    -0.06
    POSITIVE LOGITS
    🙊
    0.08
    填充
    0.07
    อำนวยความสะดวก
    0.07
     Goa
    0.07
    nesota
    0.07
    entreprise
    0.07
    콸
    0.07
    企业发展
    0.07
    当て
    0.07
    哪家好
    0.07
    Activations Density 0.286%

    No Known Activations