© 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. 31-TRANSCODER-HP
    7. 19075
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tails
    -0.31
    .INSTANCE
    -0.31
     commuter
    -0.27
    AMENT
    -0.26
     ment
    -0.26
    ä¸ĵ项
    -0.25
     evid
    -0.25
    ockets
    -0.25
     Pall
    -0.24
    尾巴
    -0.24
    POSITIVE LOGITS
    å¥Ī
    0.30
    Formats
    0.30
     Description
    0.26
    =num
    0.26
     Font
    0.25
    azes
    0.25
     Include
    0.25
    Include
    0.25
    ahi
    0.24
    (Font
    0.24
    Activations Density 1.242%

    No Known Activations