© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 24831
    Prev
    Next
    INDEX
    Explanations

    Business-related, formal documents

    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
    request
    -0.38
    Request
    -0.37
     request
    -0.36
    upon
    -0.36
    æĪijåı¯ä»¥
    -0.35
     upon
    -0.34
    available
    -0.33
    è«ĭæ±Ĥ
    -0.32
     Request
    -0.32
    .request
    -0.31
    POSITIVE LOGITS
    缴è¾ĸå¸Ĥ
    0.25
    åĪ°åºķ
    0.25
    è¾¾å°Ķ
    0.25
    stringLiteral
    0.24
    imson
    0.24
    æĭ´
    0.24
    .ReadAll
    0.23
    è¾¾ä¸įåĪ°
    0.23
    ä¸ĢæŶ
    0.23
     Äijua
    0.23
    Activations Density 0.005%

    No Known Activations