© 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. 25-TRANSCODER-HP
    7. 107160
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Lancaster
    -0.25
    umption
    -0.24
    ç»ĪçĶŁ
    -0.24
    .instant
    -0.24
    é¢Ĩè·ij
    -0.24
    دÙĨ
    -0.24
    é²Ń
    -0.24
    AttributeName
    -0.24
     renew
    -0.24
    bang
    -0.24
    POSITIVE LOGITS
    /misc
    0.28
    radi
    0.25
     chances
    0.25
    ãģ¨ãĤĬ
    0.25
    ä½łçľĭ
    0.24
    terminate
    0.24
    adel
    0.24
    terraform
    0.24
     chance
    0.23
    esc
    0.23
    Activations Density 0.169%

    No Known Activations

    This feature has no known activations.