© 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. 63162
    Prev
    Next
    INDEX
    Explanations

    in this respect, regard, aspect, sense

    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
     Rodrig
    -0.08
    æĸ°æ°ij
    -0.08
    amedi
    -0.07
    ä¸įå¤ļçļĦ
    -0.07
    æľ¬æĸĩéĵ¾æİ¥
    -0.07
    nikov
    -0.07
    æīĢåľ¨
    -0.07
    ibri
    -0.07
    ä¹ĭæīį
    -0.07
    顾åIJįæĢĿ
    -0.07
    POSITIVE LOGITS
    æĸ¹éĿ¢çļĦ
    0.10
    æĸ¹éĿ¢
    0.08
    çŃīæĸ¹éĿ¢çļĦ
    0.08
    ä¸ĭåĬŁå¤«
    0.07
    æĸ¹éĿ¢æľī
    0.07
    çŃīæĸ¹éĿ¢
    0.07
    åİĭåĢĴ
    0.07
    åİ»ä½ķ
    0.07
    åģļåĪ°
    0.07
    è¿Ļæĸ¹éĿ¢
    0.07
    Activations Density 0.075%

    No Known Activations