© 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. 19255
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    alte
    -0.29
    MapView
    -0.27
    irteen
    -0.26
    elve
    -0.24
    大家åĪĨ享
    -0.24
    pire
    -0.23
    /Table
    -0.23
    :///
    -0.23
     '**
    -0.23
    gram
    -0.23
    POSITIVE LOGITS
    ÃĹ
    0.89
     ÃĹ
    0.78
    x
    0.55
    -by
    0.52
    \t
    0.51
    by
    0.50
    ÃĹ↵↵
    0.49
    ⨯
    0.46
     by
    0.44
    times
    0.43
    Activations Density 18.556%

    No Known Activations