© 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. 5989
    Prev
    Next
    INDEX
    Explanations

    ahead or behind

    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
    ä¿ĿæĬ¤åĮº
    -0.29
     mux
    -0.27
    好çļĦ
    -0.26
    anic
    -0.25
    æĦıä¹īä¸ĬçļĦ
    -0.25
     cancelButton
    -0.24
    è´¨
    -0.24
    åĩŃ
    -0.23
     Lawson
    -0.23
    uç
    -0.23
    POSITIVE LOGITS
    ción
    0.29
    _IPV
    0.27
    uml
    0.26
     towards
    0.25
    ittal
    0.24
    赤
    0.24
     toward
    0.24
    reland
    0.24
    erala
    0.23
     Bog
    0.23
    Activations Density 0.056%

    No Known Activations