© 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. 22518
    Prev
    Next
    INDEX
    Explanations

    stop emission or continuation

    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
    วัล
    -0.10
    rvine
    -0.10
    ually
    -0.10
    enticator
    -0.09
    ลัà¸ģษà¸ĵà¹Į
    -0.09
    pired
    -0.09
    оÑĤе
    -0.09
    zaam
    -0.09
    uality
    -0.09
    æݧèĤ¡æľīéĻIJåħ¬åı¸
    -0.09
    POSITIVE LOGITS
    ä¸ĭæĿ¥çļĦ
    0.09
    ä¸įä¸ĭæĿ¥
    0.08
    ä¸įåīį
    0.08
    ting
    0.08
    aneous
    0.07
    ä¸įä½ıçļĦ
    0.07
    گاÙĩ
    0.07
    abble
    0.07
    ax
    0.07
    acked
    0.07
    Activations Density 0.027%

    No Known Activations