© 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. 13726
    Prev
    Next
    INDEX
    Explanations

    maximum

    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
    ä¸İåħ¶ä»ĸ
    -0.07
     fit
    -0.06
     law
    -0.06
    AREN
    -0.06
    law
    -0.06
     chôm
    -0.06
    åıĬåħ¶å®ĥ
    -0.06
    æĪĸ被
    -0.06
     do
    -0.06
    ç«¥åŃIJ
    -0.06
    POSITIVE LOGITS
    imax
    0.10
    æĺ¯æľĢ
    0.09
    MAX
    0.09
    rlen
    0.08
    æľĢ强çļĦ
    0.08
     maxi
    0.08
    =max
    0.08
     máxima
    0.08
    æľĢå·®
    0.07
    alach
    0.07
    Activations Density 0.009%

    No Known Activations