© 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. 43465
    Prev
    Next
    INDEX
    Explanations

    design and designers

    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
    å®īåħ¨ç¨³å®ļ
    -0.07
     drilled
    -0.07
    家åºŃåĴĮ
    -0.06
     Security
    -0.06
    æķĻåŃ¦æ°´å¹³
    -0.06
     thunder
    -0.06
    ä¸Ģ声
    -0.06
     patched
    -0.06
    ä¸ĢèĪ¬
    -0.06
     Statistics
    -0.06
    POSITIVE LOGITS
     designers
    0.13
    设计å¸Ī
    0.13
    æıIJæ¡Ī
    0.12
    /design
    0.12
     design
    0.12
    ä¸İ设计
    0.11
     дизайнеÑĢ
    0.11
     návr
    0.11
    审ç¾İ
    0.11
     designing
    0.11
    Activations Density 0.443%

    No Known Activations