© 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. 32-TRANSCODER-HP
    7. 41482
    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_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asmus
    -0.26
     Masters
    -0.25
    ëĮĢë¡ľ
    -0.24
    饷
    -0.23
    querque
    -0.23
     Dash
    -0.23
    .Buffer
    -0.23
    ä¸įåĩº
    -0.23
    pus
    -0.23
    /rfc
    -0.23
    POSITIVE LOGITS
     the
    0.42
    the
    0.38
    —the
    0.36
     then
    0.33
     tends
    0.32
     gives
    0.32
    The
    0.30
     equals
    0.30
    该
    0.29
    ä¼ļ被
    0.28
    Activations Density 0.002%

    No Known Activations