© 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. 46550
    Prev
    Next
    INDEX
    Explanations

    earlier or originally

    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
    åı¯ä»¥éĩĩåıĸ
    -0.07
    è¿Ļæł·å°±åı¯ä»¥
    -0.07
    ç¤
    -0.07
     coni
    -0.06
    ä»İèĢĮå®ŀçİ°
    -0.06
     conf
    -0.06
    带åİ»
    -0.06
    éĥ½èĥ½çľĭåĪ°
    -0.06
     audi
    -0.06
    poj
    -0.06
    POSITIVE LOGITS
     earlier
    0.12
    æĹ©äºĽ
    0.11
     Earlier
    0.11
    Earlier
    0.10
    ä¹ĭåīį
    0.09
    æĿ¥æºIJäºİ
    0.09
    ä¹ĭåīįåľ¨
    0.08
     ÑĢанее
    0.08
     originally
    0.08
     previously
    0.08
    Activations Density 0.004%

    No Known Activations