© 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. 65531
    Prev
    Next
    INDEX
    Explanations

    countries and cities

    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
    æµ·çĩķ
    -0.08
    è¿Ľåİ»
    -0.08
    è¿ĽæĿ¥
    -0.08
    åħ¶æŀĹ
    -0.08
    åľ¨è¿Ļæł·çļĦ
    -0.08
    å¾ĢéĩĮ
    -0.07
    è¿Ľåİ»äºĨ
    -0.07
    ouncil
    -0.07
    äºĨè¿Ľåİ»
    -0.07
     Russo
    -0.07
    POSITIVE LOGITS
    éĢĶä¸Ń
    0.07
    éĢĹçķĻ
    0.07
     whence
    0.07
    eshire
    0.07
     vern
    0.07
    opp
    0.07
    Suit
    0.07
    ä¸Ģ个åı«
    0.07
    ä¸īè§Ĵ
    0.07
    æ»ŀçķĻ
    0.06
    Activations Density 0.325%

    No Known Activations