© 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. 3254
    Prev
    Next
    INDEX
    Explanations

    division operations

    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
    èv
    -0.07
    èĬ®
    -0.07
    باع
    -0.07
    å¨ĺ
    -0.07
    isify
    -0.07
    oop
    -0.07
    ÙĩاÙħ
    -0.07
    çļĦä¸ĢåĪĩ
    -0.07
    ÃŃv
    -0.07
    ×ĺ×Ļפ
    -0.07
    POSITIVE LOGITS
    Dispatch
    0.07
    .dispatch
    0.07
    wb
    0.07
    rob
    0.07
     proven
    0.06
    æľīä½ł
    0.06
    _dispatch
    0.06
    -native
    0.06
     Broken
    0.06
     Torn
    0.06
    Activations Density 0.078%

    No Known Activations