© 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. 11494
    Prev
    Next
    INDEX
    Explanations

    end of section or list

    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
    oppers
    -0.08
    åįĹæ¹ĸ
    -0.08
    åįĬåľº
    -0.08
    å¿ĥçĶĺ
    -0.08
    ezd
    -0.08
    èĢĮä¸Ķåľ¨
    -0.07
     Manson
    -0.07
    inak
    -0.07
    orex
    -0.07
     Alegre
    -0.07
    POSITIVE LOGITS
    avery
    0.06
    Ø´ÛĮ
    0.06
    ald
    0.06
     biên
    0.06
    culus
    0.06
    Padding
    0.06
    æľīçĽĬ
    0.06
     Editor
    0.06
    çĥŃ线çĶµè¯Ŀ
    0.06
    t
    0.06
    Activations Density 0.051%

    No Known Activations