© 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. 1239
    Prev
    Next
    INDEX
    Explanations

    numerical expressions with exponents

    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
    鸣è¯Ń
    -0.09
    checker
    -0.08
    -export
    -0.08
    åķ¬
    -0.08
    gom
    -0.08
     mắt
    -0.08
    oldt
    -0.08
    æľīå¾ħ
    -0.08
    æľªåĪ°
    -0.08
    è¿ĺæľīå¾ħ
    -0.08
    POSITIVE LOGITS
     irrespective
    0.07
    éĻ¶
    0.07
    eger
    0.07
     regardless
    0.07
    æĹłè®º
    0.07
     universal
    0.07
    Regardless
    0.06
     always
    0.06
     universally
    0.06
    æĭ±
    0.06
    Activations Density 0.006%

    No Known Activations