© 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. 30-TRANSCODER-HP
    7. 96965
    Prev
    Next
    INDEX
    Explanations

    %

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä»·åĢ¼
    -0.42
     value
    -0.40
    value
    -0.40
    èĤ¡
    -0.39
    åĥ¹åĢ¼
    -0.36
    åĢ¼
    -0.33
    	value
    -0.32
     Value
    -0.32
    Value
    -0.31
     VALUE
    -0.30
    POSITIVE LOGITS
    yah
    0.31
    iswa
    0.26
    æļ´éľ²
    0.26
    éľ²å¤©
    0.26
    isphere
    0.26
    æĸ°éĻĪ代谢
    0.26
    ç»ı纬
    0.25
    ç¾İ人
    0.25
    ç±»
    0.25
    类产åĵģ
    0.25
    Activations Density 0.914%

    No Known Activations