© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51847
    Prev
    Next
    INDEX
    Explanations

    additional deaths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -0.08
    åķĨ
    -0.07
    æľīæĽ´å¤ļçļĦ
    -0.06
    ä¸Ģ个æĸ°çļĦ
    -0.06
    ette
    -0.06
    acle
    -0.06
    æĺ¯å¦Ĥä½ķ
    -0.06
    就好åĥı
    -0.06
    ®
    -0.06
    è¿«
    -0.06
    POSITIVE LOGITS
    CLU
    0.08
    FileStream
    0.08
    EAU
    0.08
    زÙĦ
    0.08
    asia
    0.08
    AMPL
    0.08
    ãģ®å¤ī
    0.08
    osh
    0.08
    _formatter
    0.08
    Ñĥго
    0.08
    Activations Density 0.001%

    No Known Activations