© 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. 58122
    Prev
    Next
    INDEX
    Explanations

    explaining the unknown or unfamiliar

    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
    æĪijè¦ģè¯Ħ论
    -0.07
    涧
    -0.07
     pattern
    -0.07
    åİ»éĿ¢å¯¹
    -0.06
    ApiResponse
    -0.06
    anga
    -0.06
     patter
    -0.06
     ÑĥÑģк
    -0.06
    ä¸Ĭ交
    -0.06
    ç»®
    -0.06
    POSITIVE LOGITS
     prerequisite
    0.10
    éĵºåŀ«
    0.10
    解éĩĬ
    0.10
    åŁºç¡ĢçŁ¥è¯Ĩ
    0.10
     ÑĢазÑĬÑıÑģ
    0.10
     unfamiliar
    0.09
     explanation
    0.09
     clarification
    0.09
    æĸ°æ¦Ĥ念
    0.09
    ä¸įçĨŁæĤī
    0.09
    Activations Density 0.177%

    No Known Activations