© 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. 22395
    Prev
    Next
    INDEX
    Explanations

    conversion and change

    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
     recently
    -0.07
    zil
    -0.06
    olio
    -0.06
    ($)
    -0.06
    lessly
    -0.06
    æĢ§æĪĸ
    -0.06
    æĮ½
    -0.06
    иÑĤелÑĮно
    -0.06
     Cre
    -0.06
    |null
    -0.06
    POSITIVE LOGITS
    è¿ĩç¨ĭä¸Ń
    0.10
    à¸Ħรัà¹īà¸ĩà¸Ļีà¹ī
    0.10
    vorg
    0.09
    为å¥ijæľº
    0.09
     xong
    0.09
    è¿ĩç¨ĭ
    0.08
    è¿ĩç¨ĭä¸ŃçļĦ
    0.08
    éģİç¨ĭä¸Ń
    0.08
    ãģ«ä¼´
    0.08
    -induced
    0.08
    Activations Density 0.035%

    No Known Activations