© 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. 5884
    Prev
    Next
    INDEX
    Explanations

    data processing

    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
    滩
    -0.29
    osal
    -0.29
    马路
    -0.28
    纡
    -0.26
    褥
    -0.26
    è¹Ĵ
    -0.26
    æµ·æ¹¾
    -0.26
    ä¾Ŀ
    -0.25
    毯
    -0.25
    cÃŃ
    -0.25
    POSITIVE LOGITS
     cube
    0.44
     Cube
    0.40
     cubes
    0.38
    ç«ĭæĸ¹
    0.37
     volume
    0.36
    (cube
    0.36
    volume
    0.35
     Volume
    0.34
    _cube
    0.33
    ç«ĭä½ĵ
    0.32
    Activations Density 0.090%

    No Known Activations