© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48619
    Prev
    Next
    INDEX
    Explanations

    open-end spinning, long track, fly rod, rabbitfish

    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
    论
    -0.07
    æİĮ
    -0.06
     worth
    -0.06
    ilo
    -0.06
    (nameof
    -0.06
    estro
    -0.05
    SO
    -0.05
     Sop
    -0.05
    olla
    -0.05
    Ïģί
    -0.05
    POSITIVE LOGITS
    adÃŃ
    0.09
    żd
    0.08
    æĬĵèIJ½å®ŀ
    0.08
    /GPL
    0.08
    incinn
    0.08
    èµŀè¿ĩ
    0.08
    æł¸å¿ĥåĽ¢éĺŁ
    0.08
    æľīæĿĥä¿ĿçķĻ
    0.08
    ühl
    0.08
     STYLE
    0.08
    Activations Density 0.313%

    No Known Activations