© 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. 38608
    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
    æĬ¤
    -0.24
     clashes
    -0.23
    ç§į
    -0.23
     Competitive
    -0.23
    ç³»
    -0.23
    åĪ¶æľį
    -0.23
    æ±Ĥ
    -0.23
    çĪ±åĽ½
    -0.23
    åIJĮç±»
    -0.22
    éĺ²çº¿
    -0.22
    POSITIVE LOGITS
    ango
    0.29
    cox
    0.28
    sey
    0.27
    ice
    0.25
    unda
    0.25
    管çIJĨä¸Ńå¿ĥ
    0.25
    iken
    0.24
    embers
    0.24
    ByKey
    0.23
    âĶĦ
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.