© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96591
    Prev
    Next
    INDEX
    Explanations

    Question/quote punctuation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     whether
    -0.71
    whether
    -0.60
    Whether
    -0.57
     Whether
    -0.57
    æĺ¯åIJ¦
    -0.53
     æĺ¯åIJ¦
    -0.49
    æĺ¯åIJ¦ä¼ļ
    -0.44
     WHETHER
    -0.43
    æĺ¯åIJ¦åŃĺåľ¨
    -0.42
    æĺ¯åIJ¦æľī
    -0.42
    POSITIVE LOGITS
    çļĦç¡®
    0.39
    ç¡®
    0.34
    ç¡®å®ŀ
    0.33
    ä¸įä¸ĭ
    0.31
    ¦Ĥ
    0.31
     Indeed
    0.29
    æŀģå°ij
    0.28
    確
    0.28
    Indeed
    0.27
     No
    0.27
    Activations Density 0.905%

    No Known Activations