© 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. 18725
    Prev
    Next
    INDEX
    Explanations

    networking

    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
    _Save
    -0.07
    <V
    -0.07
    问询
    -0.07
    的经验
    -0.07
    千方
    -0.07
    ydı
    -0.07
    都有着
    -0.06
    阴
    -0.06
    …↵↵↵↵
    -0.06
    ,content
    -0.06
    POSITIVE LOGITS
    _portfolio
    0.07
    Real
    0.07
    aptive
    0.07
    redit
    0.07
     malloc
    0.07
     radiator
    0.07
    0.06
     Falk
    0.06
    literal
    0.06
    (proxy
    0.06
    Activations Density 0.018%

    No Known Activations