© 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. 42862
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    "
    -0.49
    (
    -0.42
    \n
    -0.41
    '
    -0.38
    <br
    -0.36
    [
    -0.35
    -
    -0.35
    ”
    -0.35
    \t
    -0.34
    \r
    -0.34
    POSITIVE LOGITS
     etc
    0.36
     &,
    0.34
    etc
    0.32
     and
    0.31
    __,__
    0.31
    å°¤åħ¶æĺ¯
    0.31
     ê·¸ë¦¬ê³ł
    0.30
    _,
    0.29
     ",",
    0.29
    +,
    0.29
    Activations Density 0.046%

    No Known Activations