© 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. 19965
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    oubles
    -0.28
     bringing
    -0.25
    ems
    -0.25
    -fold
    -0.25
     bring
    -0.25
    ãĤ¸ãĥ£ãĥ¼
    -0.25
    è¡Į使
    -0.24
    Bring
    -0.24
    marshall
    -0.24
    .AddRange
    -0.24
    POSITIVE LOGITS
    rets
    0.32
    .tail
    0.28
    OV
    0.28
     kg
    0.26
    NCY
    0.25
    outed
    0.25
    å¼
    0.24
    åĬ¨äºº
    0.24
    tol
    0.24
     OV
    0.24
    Activations Density 0.001%

    No Known Activations