© 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. 94562
    Prev
    Next
    INDEX
    Explanations

    Introductions and establishments

    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
     thúc
    -0.07
    updated
    -0.07
    核酸检测
    -0.07
     Tribute
    -0.07
     ID
    -0.06
     erased
    -0.06
     SAMPLE
    -0.06
    观测
    -0.06
     History
    -0.06
    侵略
    -0.06
    POSITIVE LOGITS
    嗉
    0.09
    🍥
    0.08
    Coffee
    0.07
     الشركة
    0.07
    –↵↵
    0.06
    rink
    0.06
    שפע
    0.06
    ꧈
    0.06
    -Free
    0.06
     colabor
    0.06
    Activations Density 0.199%

    No Known Activations