© 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. 24616
    Prev
    Next
    INDEX
    Explanations

    logarithm and math functions

    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
     Natale
    -0.09
    itiva
    -0.08
    лиÑģÑĤÑĭ
    -0.08
     Ø°Ùĩ
    -0.08
    اÙģر
    -0.08
    èį
    -0.08
    hawk
    -0.07
    _WATCH
    -0.07
     SharedModule
    -0.07
    stens
    -0.07
    POSITIVE LOGITS
    auge
    0.07
    culus
    0.07
     logarith
    0.06
    arit
    0.06
    è¿IJç®Ĺ
    0.06
    åıijèĩª
    0.06
    åľı
    0.06
    èĥ¸èĨĽ
    0.06
    emar
    0.06
    /vendor
    0.06
    Activations Density 0.002%

    No Known Activations