© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7060
    Prev
    Next
    INDEX
    Explanations

    court case citations

    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
    Negative Logits
    éģµå®ĪåĽ½å®¶
    -0.07
    kup
    -0.07
    éph
    -0.07
    çŃĸåĪĴ
    -0.06
    æ³¢åıĬ
    -0.06
    initely
    -0.06
    ä»Ģä¹Īåij¢
    -0.06
    ç§Ĩ
    -0.06
     xo
    -0.06
    æv
    -0.06
    POSITIVE LOGITS
    åĪ¤æĸŃé¢ĺ
    0.11
    UMB
    0.08
    sigmoid
    0.08
    обÑĢаз
    0.08
    gili
    0.08
    reti
    0.07
    abcdefgh
    0.07
    PECT
    0.07
    auge
    0.07
     calibre
    0.07
    Activations Density 0.010%

    No Known Activations