© 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. 8127
    Prev
    Next
    INDEX
    Explanations

    variable assignments with code elements

    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
    dere
    -0.08
    dol
    -0.08
    åħ¼æĢ»ç»ıçIJĨ
    -0.07
    #__
    -0.07
    çŀ
    -0.07
     inkl
    -0.07
     eds
    -0.07
    龸çİĭ
    -0.07
    elter
    -0.07
    è·Ľ
    -0.07
    POSITIVE LOGITS
    æĺ¯ä¸Ģ个å¾Ī
    0.09
     supposed
    0.08
    æĺ¯ä¸Ģ个
    0.08
    æĺ¯ä¸Ģ个éĿŀ常
    0.08
    æĺ¯ä¸ĢåĢĭ
    0.08
    è¿Ļ个åIJįåŃĹ
    0.08
    å®ļä¹ī为
    0.08
    临
    0.08
     supposedly
    0.07
    æĺ¯ä¸ª
    0.07
    Activations Density 0.019%

    No Known Activations