© 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. 60652
    Prev
    Next
    INDEX
    Explanations

    ion with suffixes like -ized, -izable

    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
    à¸ģารà¸ĵà¹Į
    -0.09
    ÑģлÑĮ
    -0.09
    æĤ¨åı¯èĥ½
    -0.08
    ters
    -0.08
    æ·ĭæ¼ĵ
    -0.08
    Ø©
    -0.07
    unts
    -0.07
    ence
    -0.07
    NESS
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    POSITIVE LOGITS
    ized
    0.11
    à§įড
    0.11
    zinho
    0.10
    cake
    0.10
    izable
    0.09
    ogenic
    0.08
    nection
    0.08
    ãģ£ãģ±
    0.08
    fert
    0.08
    à¸ļวà¸ģ
    0.08
    Activations Density 0.032%

    No Known Activations