© 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. 16635
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and expressions

    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
    ↵     ↵
    -0.08
    abaya
    -0.07
    aber
    -0.07
    iless
    -0.07
    å¿ĹåĪļ
    -0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
    ↵   ↵
    -0.06
     profitable
    -0.06
     emozion
    -0.06
    onie
    -0.06
    POSITIVE LOGITS
    umper
    0.08
    uai
    0.08
    สà¸ķ
    0.07
    unicode
    0.07
    iform
    0.06
    ypes
    0.06
    uduk
    0.06
    opedia
    0.06
    éra
    0.06
    intl
    0.06
    Activations Density 0.035%

    No Known Activations