© 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. 18843
    Prev
    Next
    INDEX
    Explanations

    educational backgrounds

    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
    地带
    -0.08
    中国大陆
    -0.07
    ReLU
    -0.07
     בהם
    -0.07
    Handles
    -0.07
    眼前的
    -0.07
     אותן
    -0.07
     GL
    -0.07
    Dave
    -0.06
    꿕
    -0.06
    POSITIVE LOGITS
    iling
    0.08
    ɥ
    0.07
     Riy
    0.07
     dec
    0.07
     октя
    0.07
    alous
    0.06
     Lexington
    0.06
     THEN
    0.06
    젝
    0.06
    ῄ
    0.06
    Activations Density 0.044%

    No Known Activations