© 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. 61379
    Prev
    Next
    INDEX
    Explanations

    mathematical formula or equation

    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
    è¿Ļæī¹
    -0.09
    è¿Ļ群
    -0.08
    imulator
    -0.08
    è¿Ļç§įæĦŁè§ī
    -0.08
    éĺħè¯»æľ¬æĸĩåīį
    -0.07
    好ç¬ij
    -0.07
    -handler
    -0.07
    inspace
    -0.07
    éri
    -0.07
    icali
    -0.07
    POSITIVE LOGITS
    åħ¬å¼ı
    0.13
     formula
    0.13
     equation
    0.12
     formulas
    0.11
     equations
    0.11
    æĸ¹ç¨ĭå¼ı
    0.11
    formula
    0.10
    æĸ¹ç¨ĭ
    0.09
    å¼ıåĴĮ
    0.09
     formule
    0.09
    Activations Density 0.026%

    No Known Activations