© 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. 22-TRANSCODER-HP
    7. 99003
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĨħç½®
    -0.28
    éķ¶åµĮ
    -0.24
    åĨĹ
    -0.24
     Cler
    -0.24
     right
    -0.24
     Prä
    -0.23
    æŁIJ
    -0.23
    æ¢Ŀ
    -0.23
    æĿ¡
    -0.23
    nan
    -0.23
    POSITIVE LOGITS
    è¿ĻäºĽéĥ½æĺ¯
    0.41
    éĥ½ä¸įæĺ¯
    0.31
    åĿĩ为
    0.30
    è¿Ļ两个
    0.30
    è¿Ļ两ç§į
    0.28
    éĥ½æĺ¯
    0.28
    è¿ĻäºĽ
    0.28
    è¿ĻäºĽéĹ®é¢ĺ
    0.28
    è¿ĻäºĽä¸ľè¥¿
    0.27
    çļĨ
    0.27
    Activations Density 0.006%

    No Known Activations