© 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. 5870
    Prev
    Next
    INDEX
    Explanations

    Code and mathematical formulas

    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¸ŃéĹ´
    -0.45
    å¾Ģè¿Ķ
    -0.44
    è¿Ľåĩº
    -0.42
    å¾ĢæĿ¥
    -0.39
    æĿ¥åĽŀ
    -0.39
    两端
    -0.39
    ±
    -0.39
     +/-
    -0.38
    两边
    -0.37
     middle
    -0.36
    POSITIVE LOGITS
    ä¸įæĸŃåĪĽæĸ°
    0.28
    è®Ń
    0.27
    å¾ģæľį
    0.27
    æ±ĩ
    0.26
    ipur
    0.26
     mocks
    0.26
    mue
    0.26
    ä¸įæĸŃæıIJé«ĺ
    0.25
    vero
    0.25
    igram
    0.25
    Activations Density 0.034%

    No Known Activations