© 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. 35-TRANSCODER-HP
    7. 38907
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spa
    -0.26
    istan
    -0.25
    udos
    -0.25
    agan
    -0.24
    layui
    -0.24
    edar
    -0.23
     effected
    -0.23
    æĸIJ
    -0.23
     diy
    -0.23
    :disable
    -0.23
    POSITIVE LOGITS
    åħ¨åijĺ
    0.27
    icut
    0.27
    åħ¨å¥Ĺ
    0.26
    æĺ¯åĽ½åĨħ
    0.25
    OTH
    0.25
    onth
    0.24
    æŶéĹ´ä¸º
    0.24
    两æīĭ
    0.24
    imes
    0.24
    utes
    0.23
    Activations Density 53.515%

    No Known Activations

    This feature has no known activations.