© 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. 18026
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    uzzi
    -0.27
    TU
    -0.27
    (IntPtr
    -0.26
    hole
    -0.26
    æĮĩçĤ¹
    -0.25
     &,
    -0.25
    .pin
    -0.25
    HY
    -0.25
    -html
    -0.24
    趱
    -0.24
    POSITIVE LOGITS
    è¶ħé¢Ŀ
    0.31
    avax
    0.30
     Batter
    0.26
     psychologically
    0.26
    失èIJ½
    0.25
    IJèĹı
    0.25
    eyer
    0.25
    å¯ħ
    0.24
    WARE
    0.24
    çļĦå¿ĥçIJĨ
    0.24
    Activations Density 0.113%

    No Known Activations

    This feature has no known activations.