© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5439
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olls
    -0.28
    ева
    -0.25
    èģĬ天
    -0.25
     Lâm
    -0.24
    å·²å®ĮæĪIJ
    -0.24
    __),
    -0.24
    åħ¬ç«ĭåĮ»éĻ¢
    -0.23
    ÑĥÑī
    -0.23
    éľĩåĬ¨
    -0.23
    pletion
    -0.23
    POSITIVE LOGITS
     bul
    0.27
    ëŁī
    0.27
    antal
    0.26
    PCODE
    0.24
     count
    0.24
     sublist
    0.24
    =count
    0.24
    ç®ķ
    0.24
    é«ĺç´łè´¨
    0.23
    ç¨Ģ
    0.23
    Activations Density 0.125%

    No Known Activations