© 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. 41414
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    -bed
    -0.26
     emerges
    -0.24
    以èī²
    -0.23
    -axis
    -0.23
    è§Ĵ度æĿ¥çľĭ
    -0.23
    —that
    -0.23
    .atan
    -0.23
    arez
    -0.23
    alink
    -0.23
    <Link
    -0.23
    POSITIVE LOGITS
    in
    0.29
    èį«
    0.27
    ķĮ
    0.27
    ols
    0.26
    “
    0.26
    fully
    0.26
    å¸ĥ
    0.26
     inset
    0.25
    radius
    0.25
    DO
    0.25
    Activations Density 0.004%

    No Known Activations