© 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. 31-TRANSCODER-HP
    7. 18063
    Prev
    Next
    INDEX
    Explanations

    Biographical information

    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
    å¸Ī
    -0.31
    InstanceId
    -0.27
     spit
    -0.27
     Intl
    -0.26
    cket
    -0.26
    ecn
    -0.25
    師
    -0.25
    lica
    -0.24
    CKET
    -0.24
    é½IJ
    -0.24
    POSITIVE LOGITS
     acquiring
    0.27
    fortune
    0.27
    èĬĴ
    0.26
    æķ°çĽ®
    0.26
    alle
    0.26
    ä¼ı
    0.26
    fal
    0.25
    rang
    0.25
    .svg
    0.25
    æĹ¥åľ¨
    0.24
    Activations Density 0.002%

    No Known Activations