© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57185
    Prev
    Next
    INDEX
    Explanations

    game. or game-related elements

    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
    QualifiedName
    -0.08
    å¹´éĩĮ
    -0.07
    aring
    -0.07
    ILLA
    -0.07
    ingen
    -0.07
    ream
    -0.07
    ahl
    -0.07
     profiling
    -0.07
    -profile
    -0.07
    齿
    -0.07
    POSITIVE LOGITS
    åĽŀåIJĪ
    0.09
    arkan
    0.08
    leger
    0.07
     HUD
    0.07
     opponents
    0.07
    æª
    0.07
    éĺµ
    0.07
     UI
    0.07
    feit
    0.07
    isplay
    0.07
    Activations Density 0.184%

    No Known Activations