© 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. 109501
    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
     Ember
    -0.27
    jsc
    -0.26
    å®ļå¾ĭ
    -0.24
     Nich
    -0.24
    为æĤ¨æıIJä¾Ľ
    -0.24
    (suite
    -0.23
    åįģæľĪ
    -0.23
    è¿Ļ个è¯į
    -0.23
    ä»·æł¼ä¸Ĭ涨
    -0.23
    çĶŁçī©åѦ
    -0.22
    POSITIVE LOGITS
    å¦Ħ
    0.28
    ["@
    0.26
    æ¯Ĵ
    0.25
    çĩ®
    0.24
    mares
    0.24
     Sly
    0.24
    øj
    0.24
    顺çĿĢ
    0.23
     cinemat
    0.23
    GridLayout
    0.23
    Activations Density 0.157%

    No Known Activations

    This feature has no known activations.