© 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. 15412
    Prev
    Next
    INDEX
    Explanations

    "poslan" after Cyrillic prefixes

    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
    çļĦ
    -0.14
    ами
    -0.12
    çļĦãģª
    -0.11
    를
    -0.10
    able
    -0.10
    ÑģÑı
    -0.10
    ivec
    -0.09
    çļĦéĢĶå¾Ħ
    -0.09
    çĶ¨ä»¥
    -0.08
    andbox
    -0.08
    POSITIVE LOGITS
     ìĿ¸íķ´
    0.11
    t
    0.10
    ìį¨
    0.10
     ìĿ¸íķľ
    0.08
    ra
    0.08
    re
    0.08
    run
    0.08
    f
    0.07
    ss
    0.07
    aller
    0.07
    Activations Density 0.027%

    No Known Activations