© 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. 17794
    Prev
    Next
    INDEX
    Explanations

    coding/language errors

    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
    -collapse
    -0.31
    åıij
    -0.28
     deco
    -0.27
     decom
    -0.27
    è£Ĥ
    -0.27
    кова
    -0.26
    .Values
    -0.26
     Gest
    -0.25
    ned
    -0.25
    ROC
    -0.24
    POSITIVE LOGITS
    ometer
    0.31
    วย
    0.24
    çIJī
    0.24
    à¹Ģà¸Ńà¸ĩ
    0.23
    åľ°æ®µ
    0.23
     kepada
    0.23
    aña
    0.23
    uben
    0.23
    _AF
    0.23
    é¢ijçİĩ
    0.23
    Activations Density 0.189%

    No Known Activations