© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 52556
    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_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    (
    -0.73
    "
    -0.53
    *
    -0.46
    {
    -0.46
    [
    -0.46
    -
    -0.43
    /
    -0.40
    \
    -0.40
    .
    -0.40
    '
    -0.39
    POSITIVE LOGITS
    emploi
    0.29
    territ
    0.27
    ®,
    0.26
    liqu
    0.26
    ')č↵č↵
    0.25
    ous
    0.25
    justify
    0.25
    乸
    0.25
    etail
    0.25
    à¸ĩ
    0.25
    Activations Density 0.183%

    No Known Activations