© 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. 56633
    Prev
    Next
    INDEX
    Explanations

    inverse exponents, reciprocals

    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
    istri
    -0.08
    æľ¬æĸĩæĿ¥èĩª
    -0.08
    zal
    -0.08
    leven
    -0.08
     baku
    -0.07
    rome
    -0.07
    秫
    -0.07
    è¡Ŀ
    -0.07
    Brains
    -0.07
    æ»´æ»´
    -0.07
    POSITIVE LOGITS
     invers
    0.07
     exp
    0.07
     inverse
    0.07
     exponent
    0.07
    å°¹
    0.06
    adget
    0.06
     reciprocal
    0.06
    inverse
    0.06
    icare
    0.06
    æĬĵçĿĢ
    0.06
    Activations Density 0.005%

    No Known Activations