© 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. 27-TRANSCODER-HP
    7. 9345
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¸ıä¸Ĭ
    -0.33
     possibilities
    -0.29
    çļĦæĢ§æł¼
    -0.28
    ç¡ķ
    -0.28
    æ®ĸ
    -0.28
    æĹħéĢĶ
    -0.28
    egment
    -0.28
    è§ī
    -0.27
     boundaries
    -0.26
     exits
    -0.26
    POSITIVE LOGITS
    flation
    0.29
    æĵįä½ľ
    0.27
     pen
    0.25
    tion
    0.25
    ingroup
    0.25
    ation
    0.25
    period
    0.25
    ül
    0.25
    _wr
    0.25
    obao
    0.25
    Activations Density 0.018%

    No Known Activations