© 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. 15-RESID-POST-AA
    11. 5551
    Prev
    Next
    INDEX
    Explanations

    website content

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     forbidden
    -0.07
    ?";↵
    -0.07
    ﱰ
    -0.06
     arou
    -0.06
    USER
    -0.06
     notification
    -0.06
    وفر
    -0.06
    年产
    -0.06
    Production
    -0.06
    已完成
    -0.06
    POSITIVE LOGITS
    Ŭ
    0.08
    -Cal
    0.07
    lemetry
    0.07
    Nova
    0.07
    匦
    0.07
    Ɣ
    0.07
    uttle
    0.07
    OLF
    0.06
    ציה
    0.06
    :The
    0.06
    Activations Density 1.444%

    No Known Activations