© 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. 5877
    Prev
    Next
    INDEX
    Explanations

    Code, math, technical problems

    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
    lein
    -0.30
     silent
    -0.27
    æĹłå£°
    -0.25
    atie
    -0.25
    .Accept
    -0.24
    ken
    -0.24
    åĬ¨äºº
    -0.24
    ative
    -0.24
    eer
    -0.23
     creeping
    -0.23
    POSITIVE LOGITS
    fäll
    0.26
    åŃ¦æł¡çļĦ
    0.25
    ément
    0.25
    羯
    0.24
    mage
    0.24
    yne
    0.23
    uckle
    0.23
    å½¢æĪIJ
    0.23
    沦
    0.23
    ndata
    0.23
    Activations Density 4.775%

    No Known Activations