© 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. 24603
    Prev
    Next
    INDEX
    Explanations

    code/legal 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
     Dec
    -0.29
     As
    -0.28
    otine
    -0.28
     dec
    -0.28
     context
    -0.26
     situ
    -0.26
    __,↵
    -0.25
    edBy
    -0.25
    inars
    -0.25
     Context
    -0.24
    POSITIVE LOGITS
    ä¸ĬæĿ¥
    0.29
    è¿ĽæĿ¥
    0.28
    abal
    0.27
    ä¸Ģèµ·æĿ¥
    0.25
    semb
    0.25
    å¡ijéĢł
    0.24
    è·ŁæĪij
    0.24
    è¿Ļå¥Ĺ
    0.24
    (global
    0.24
    å°±è·Ł
    0.23
    Activations Density 0.007%

    No Known Activations