© 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. 23909
    Prev
    Next
    INDEX
    Explanations

    small, fast, licensed casino

    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
    ÑĢÑĥм
    -0.08
    æĢĿæĥ³åĴĮè¡ĮåĬ¨
    -0.07
    åıĪæľīä»Ģä¹Ī
    -0.07
    没æľīåĬŀæ³ķ
    -0.07
    æĦıæĥ³
    -0.07
    åı¯æĥ³
    -0.07
    atering
    -0.07
    ëĭ´
    -0.07
    meen
    -0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
    POSITIVE LOGITS
    å¤ļ彩
    0.08
    ancar
    0.07
     Leigh
    0.07
    alise
    0.07
    \.
    0.07
    å°ıå¹³
    0.06
    å®ļå¾ĭ
    0.06
    ç´§
    0.06
    ³³³
    0.06
     plagiar
    0.06
    Activations Density 0.019%

    No Known Activations