© 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. 97098
    Prev
    Next
    INDEX
    Explanations

    as

    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
    å¾Ģå¾Ģ
    -0.30
    often
    -0.30
     worse
    -0.29
    åı¸
    -0.27
     often
    -0.27
    ä¸Ģç¬ij
    -0.26
    æ´»ä¸ĭåİ»
    -0.26
    æĿ±è¥¿
    -0.25
    åIJ¸å¼ķåĬĽ
    -0.25
    alker
    -0.25
    POSITIVE LOGITS
     powerful
    0.30
     lucrative
    0.29
    å°Ĩè¿ij
    0.29
    å·¨
    0.29
     steep
    0.29
    æİ¥è¿ij
    0.28
     compact
    0.28
    ç´§åĩij
    0.27
    丰å¯Įå¤ļ彩
    0.27
    å¯ĨéĽĨ
    0.27
    Activations Density 0.892%

    No Known Activations