© 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. 23-TRANSCODER-HP
    7. 162641
    Prev
    Next
    INDEX
    Explanations

    cerebral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cast
    -0.28
    awai
    -0.26
    第ä¸Ģ书记
    -0.25
    hum
    -0.25
    öt
    -0.24
    iveness
    -0.24
    cedes
    -0.24
    mh
    -0.23
    e
    -0.23
    CursorPosition
    -0.23
    POSITIVE LOGITS
    好åIJ§
    0.27
     exe
    0.25
    ç½ijç»ľä¼łæĴŃ
    0.25
    sky
    0.24
    åijĬè¯īä»ĸ
    0.24
    横
    0.24
    aland
    0.23
    uff
    0.23
    媵
    0.23
    SCI
    0.23
    Activations Density 0.075%

    No Known Activations