© 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. 40596
    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
    Negative Logits
     è¡
    -0.27
    åĸĩ
    -0.26
     setEmail
    -0.25
    @@@@
    -0.25
     ker
    -0.25
     FileAccess
    -0.24
    ihar
    -0.23
    æµģ泪
    -0.23
    .Expect
    -0.23
    lox
    -0.23
    POSITIVE LOGITS
    äºĨ大éĩıçļĦ
    0.28
     landscapes
    0.27
    acies
    0.26
    olatile
    0.26
     ecosystems
    0.25
    vig
    0.25
     forests
    0.24
    大éĩıçļĦ
    0.24
    ports
    0.24
    ä¸ŃåĽ½çļĦ
    0.24
    Activations Density 0.014%

    No Known Activations

    This feature has no known activations.