Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 8129
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leness
    -0.29
    åĿIJ
    -0.27
    ç§»åĬ¨
    -0.27
     Dalton
    -0.26
    æĪIJ
    -0.25
    Zip
    -0.25
    zip
    -0.25
    èĢħ
    -0.24
     Dá»ĭch
    -0.24
    缸åħ³
    -0.24
    POSITIVE LOGITS
     contextual
    0.29
    izable
    0.26
    _prim
    0.26
     prioritize
    0.25
     pits
    0.25
    ursal
    0.25
    éĩijåŃĹ
    0.24
    éķ·æľŁ
    0.24
    ivate
    0.24
     synd
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.