© 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. 19568
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with symbols

    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
    itness
    -0.07
    åIJįåŁİ
    -0.07
    pta
    -0.07
    æ£ł
    -0.07
    ä½
    -0.07
    anked
    -0.07
    -eslint
    -0.07
    èİ·åĪ©
    -0.07
    èĸª
    -0.07
    Expose
    -0.06
    POSITIVE LOGITS
    缸åıįçļĦ
    0.08
     negative
    0.07
    çļĦåıį
    0.07
    缸åıį
    0.07
    åĴĮæݨ广
    0.07
    olis
    0.06
     opponents
    0.06
     opposite
    0.06
    -negative
    0.06
    PRESS
    0.06
    Activations Density 0.052%

    No Known Activations