© 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. 19896
    Prev
    Next
    INDEX
    Explanations

    game stats and attributes

    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
    =YES
    -0.07
    holm
    -0.07
    æ°Ľ
    -0.07
    ocene
    -0.07
    æľīåij³
    -0.07
     spia
    -0.07
    Nested
    -0.07
    ipple
    -0.07
    ÙĪج
    -0.07
    交费
    -0.06
    POSITIVE LOGITS
     stamina
    0.08
     hardness
    0.08
    æķ°åĢ¼
    0.08
    å±ŀæĢ§åĴĮ
    0.08
     accrued
    0.07
    CustomAttributes
    0.07
     Stamina
    0.07
     proficiency
    0.07
     abilities
    0.07
    åŁºç¡Ģ
    0.07
    Activations Density 0.033%

    No Known Activations