© 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. 64061
    Prev
    Next
    INDEX
    Explanations

    opinion of Police

    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
    -0.08
    丽èİİ
    -0.08
    untr
    -0.07
    evers
    -0.07
    ücks
    -0.07
    èīºæľ¯åĽ¢
    -0.07
    hati
    -0.07
    LIKELY
    -0.07
    hin
    -0.07
    мп
    -0.06
    POSITIVE LOGITS
     Crush
    0.07
     znak
    0.07
    aille
    0.07
    ç±³å°Ķ
    0.07
    ingue
    0.07
    alent
    0.06
    èĤĭ骨
    0.06
    anzi
    0.06
    ساÙĨ
    0.06
    躲éģ¿
    0.06
    Activations Density 0.096%

    No Known Activations