© 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. 19457
    Prev
    Next
    INDEX
    Explanations

    news articles

    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
    culated
    -0.33
     generated
    -0.31
    generated
    -0.31
     cropped
    -0.31
     instantiated
    -0.29
     '}
    -0.29
     adopted
    -0.28
     computed
    -0.28
    translated
    -0.28
    processed
    -0.28
    POSITIVE LOGITS
     Again
    0.27
    ’s
    0.27
    æĥľ
    0.27
    éĿ¢ä¸Ĭ
    0.27
     launches
    0.26
     confront
    0.25
    leys
    0.25
     enlist
    0.25
    rowse
    0.25
    's
    0.25
    Activations Density 1.092%

    No Known Activations