© 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. 5548
    Prev
    Next
    INDEX
    Explanations

    S

    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
    -tone
    -0.08
    .Update
    -0.07
     mainScreen
    -0.07
    现如今
    -0.07
    ẠI
    -0.07
    可能會
    -0.07
     recorder
    -0.06
    _facebook
    -0.06
    崖
    -0.06
    .prototype
    -0.06
    POSITIVE LOGITS
    (_('
    0.07
    ────
    0.06
    찰
    0.06
     دمشق
    0.06
     ailments
    0.06
    מנהל
    0.06
    );}↵
    0.06
    ="
    0.06
    蛟
    0.06
     inp
    0.06
    Activations Density 0.001%

    No Known Activations