© 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. 109298
    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
    çĸı
    -0.40
    trap
    -0.31
    åIJ¹
    -0.29
    etak
    -0.28
    .Hit
    -0.27
    voy
    -0.27
     colour
    -0.27
    æĿ¡ä»¶ä¸ĭ
    -0.26
    å±ŀäºİ
    -0.26
    ä¾Ŀæį®
    -0.26
    POSITIVE LOGITS
     (~(
    0.25
    ideo
    0.25
     Lager
    0.24
    åħ¨æĹ¥åĪ¶
    0.24
     Ross
    0.24
    鸩
    0.24
     Whats
    0.24
     fellow
    0.24
    ayer
    0.24
    _Height
    0.24
    Activations Density 0.126%

    No Known Activations

    This feature has no known activations.