© 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. 64575
    Prev
    Next
    INDEX
    Explanations

    obviously or apparently

    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
    çĥŃéŨæݨèįIJ
    -0.07
    Minimum
    -0.07
     Minimum
    -0.06
    owitz
    -0.06
     Sterling
    -0.06
     minimum
    -0.06
    wany
    -0.06
    icken
    -0.06
     bou
    -0.06
    å¾µ
    -0.06
    POSITIVE LOGITS
    è¿Ļ个æķ°åŃĹ
    0.09
    ä¸įèĻļ
    0.08
    ÙĤر
    0.07
    è£ħçĤ¹
    0.07
    _dep
    0.07
    ä¸Ń天
    0.07
    æļĤ
    0.07
    ÅĽÄĩ
    0.07
    è²ŀ
    0.07
    人åĵģ
    0.07
    Activations Density 0.001%

    No Known Activations