© 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. 30520
    Prev
    Next
    INDEX
    Explanations

    forms of roll

    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
    rophy
    -0.09
    roph
    -0.08
    ettor
    -0.08
    ï¾ŀ
    -0.08
    agara
    -0.08
    æĦıçļĦ
    -0.07
    biot
    -0.07
    faits
    -0.07
    irk
    -0.07
    éģ¨æ¸¸
    -0.07
    POSITIVE LOGITS
    à¹Ģวียà¸Ļ
    0.08
    ingly
    0.08
    ULAR
    0.07
     ëĤĺìĦľ
    0.07
    ÑĩаÑĤ
    0.07
    èĩªå¦Ĥ
    0.07
    ä¸įæĥĬ
    0.07
    ä¸įæģ¯
    0.07
    ularity
    0.07
    [__
    0.07
    Activations Density 0.031%

    No Known Activations