© 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. 38615
    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
    èĪ¶
    -0.29
    è¿Ļå¼ł
    -0.27
    èĪĮ头
    -0.26
    æĤ¨çļĦåŃ©åŃIJ
    -0.25
    ICC
    -0.25
    æī°
    -0.25
    çķ¸
    -0.25
    åģ¶åĥı
    -0.25
    CI
    -0.24
    åĵģçīĮçļĦ
    -0.24
    POSITIVE LOGITS
     research
    0.29
     risk
    0.28
    lla
    0.27
     limited
    0.27
     barrel
    0.27
    atore
    0.26
    anta
    0.26
    igate
    0.25
    atory
    0.25
    avian
    0.25
    Activations Density 1.110%

    No Known Activations

    This feature has no known activations.