© 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. 35048
    Prev
    Next
    INDEX
    Explanations

    win-win situation

    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
    è´¿èµĤ
    -0.07
    èĮģ壮
    -0.07
    ]*)
    -0.06
    ps
    -0.06
    ib
    -0.06
    å¤ļå¤ļå°ij
    -0.06
    ä½Ĩåħ¶å®ŀ
    -0.06
    è¡ĹåĿĬ
    -0.06
    æľĢç»ĪåıĹçĽĬ
    -0.06
    ä½ľä¸ºåĽ½åĨħ
    -0.06
    POSITIVE LOGITS
    æĬĵèIJ½å®ŀ
    0.09
    çīĮåŃIJ
    0.08
    æĬĵ好
    0.08
    æľįåĬ¡åħ¬åı¸
    0.08
    ä¸Ĭä¸ĭåĬŁå¤«
    0.08
    ignes
    0.07
    æĬĵæīĭ
    0.07
    管çĶ¨
    0.07
    çıŃåŃIJ
    0.07
    æĢĿ
    0.07
    Activations Density 0.004%

    No Known Activations