© 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. 43361
    Prev
    Next
    INDEX
    Explanations

    irrationality, transcendence, number theory

    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
    htable
    -0.09
    elow
    -0.09
    áŁĩ
    -0.09
    æī¬å¸Ĩ
    -0.09
    sdale
    -0.09
    æļ´é£Ł
    -0.08
    æĸ°ç¤¾
    -0.08
    èĴ¸èĴ¸æĹ¥ä¸Ĭ
    -0.08
    блÑİ
    -0.08
    ceo
    -0.08
    POSITIVE LOGITS
    ness
    0.08
    ä¸įåı¯
    0.08
     irrational
    0.07
    ìĨ¡
    0.06
    éĻª
    0.06
    Wrapped
    0.06
     decimal
    0.06
    æĺ¯ä¸įåı¯
    0.06
    æŃª
    0.06
    æ¯į
    0.06
    Activations Density 0.005%

    No Known Activations