© 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. 109404
    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
    ä¸ĢèĪ¬
    -0.29
    eria
    -0.27
    pow
    -0.26
    解
    -0.26
    isper
    -0.26
    (cont
    -0.24
    èĵį
    -0.24
    以ä¸Ĭ
    -0.24
    æĽ´å¥½
    -0.24
    éķĺ
    -0.24
    POSITIVE LOGITS
     abandon
    0.27
     forge
    0.27
     inade
    0.26
     course
    0.25
     eyes
    0.25
     Reeves
    0.25
     discussion
    0.25
    ounding
    0.25
     discussions
    0.24
    çĶŁäº§åĴĮ
    0.24
    Activations Density 0.080%

    No Known Activations

    This feature has no known activations.