© 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. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 19679
    Prev
    Next
    INDEX
    Explanations

    meetings or gatherings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľ¬ç«Ļ
    -0.27
    å°ıç¼ĸ
    -0.27
     presents
    -0.27
     rootNode
    -0.26
    è¿Ļå¼ł
    -0.26
     rust
    -0.25
    ISC
    -0.25
     dotyczÄħce
    -0.25
    é¦Ļ
    -0.25
    æ³½
    -0.25
    POSITIVE LOGITS
    çīĻ齿
    0.28
     mee
    0.26
    indh
    0.26
     Genetic
    0.26
     TypeName
    0.26
    -license
    0.25
    .mybatisplus
    0.25
    ::_('
    0.25
     genetics
    0.25
     Genetics
    0.25
    Activations Density 0.203%

    No Known Activations