© 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. 18128
    Prev
    Next
    INDEX
    Explanations

    /

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĵį
    -0.28
    åįĬ
    -0.28
     SD
    -0.28
    åѦéĻ¢
    -0.27
    sst
    -0.27
    导
    -0.27
    atee
    -0.26
    æīĴ
    -0.26
    éľ²åĩº
    -0.26
    åIJĪæĪIJ
    -0.26
    POSITIVE LOGITS
     plan
    0.30
    #End
    0.27
    plan
    0.26
     má»iji
    0.26
    .spi
    0.25
    dsp
    0.25
     Genius
    0.25
    çļĩä¸Ĭ
    0.24
     план
    0.24
    .raw
    0.24
    Activations Density 0.049%

    No Known Activations