© 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. 19787
    Prev
    Next
    INDEX
    Explanations

    code and math

    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
    Negative Logits
    UPPORT
    -0.27
    .nan
    -0.26
    rather
    -0.25
     milan
    -0.25
     Abort
    -0.25
    Abort
    -0.25
    _once
    -0.24
    æ°§
    -0.24
    /groups
    -0.24
    .getTag
    -0.24
    POSITIVE LOGITS
    usk
    0.29
    ası
    0.29
    isty
    0.27
     ais
    0.26
    ints
    0.25
     no
    0.25
    declare
    0.25
    epad
    0.24
     {}:
    0.24
     Uph
    0.24
    Activations Density 0.324%

    No Known Activations