© 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. 64865
    Prev
    Next
    INDEX
    Explanations

    suffixes and suffixes

    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
     \""
    -0.06
    ä¸ĢæŦ
    -0.06
    pretty
    -0.06
    尽管
    -0.06
    æ¶Ī
    -0.06
    ls
    -0.06
     Accounts
    -0.06
    ª
    -0.06
    ionate
    -0.06
     advent
    -0.06
    POSITIVE LOGITS
    为åģļ好
    0.09
    볨
    0.08
    à¤ŀ
    0.07
    人çļĦä¸ĢçĶŁ
    0.07
    LEE
    0.07
    endah
    0.07
    kob
    0.07
    FLT
    0.07
    klus
    0.07
    ë¥
    0.07
    Activations Density 0.207%

    No Known Activations