© 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. 39660
    Prev
    Next
    INDEX
    Explanations

    code and technical symbols

    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
    hend
    -0.07
    leden
    -0.07
     *}
    -0.07
    блÑİ
    -0.07
    åĩ¯è¿ª
    -0.07
    ä¹ĭçľ¼
    -0.07
    à¥įरà¥ĭ
    -0.07
    icoli
    -0.07
    AndGet
    -0.07
    иÑĤаÑĢ
    -0.07
    POSITIVE LOGITS
    Ø©
    0.07
    ender
    0.07
    ·
    0.07
    ométr
    0.07
    anger
    0.07
    ss
    0.07
    åı¸éķ¿
    0.06
     ëĤĺìĦľ
    0.06
    راÙģ
    0.06
    omat
    0.06
    Activations Density 0.014%

    No Known Activations