© 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. 20-TRANSCODER-HP
    7. 108508
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å±Ģ
    -0.29
    çŃĶ
    -0.25
    æ¢Ń
    -0.25
    req
    -0.25
    fect
    -0.25
     legitimacy
    -0.24
    åĩĿ
    -0.24
    çļĦè¦ģæ±Ĥ
    -0.24
     dungeon
    -0.24
    draft
    -0.24
    POSITIVE LOGITS
     iov
    0.27
    hots
    0.25
    çŃ¾çº¦
    0.25
    çĻ½æĸij
    0.25
    è¹Ĥ
    0.24
     tooth
    0.23
     sunk
    0.23
    urv
    0.23
    çīĻ齿
    0.23
     cân
    0.23
    Activations Density 14.202%

    No Known Activations

    This feature has no known activations.