© 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. 38260
    Prev
    Next
    INDEX
    Explanations

    how to, where to

    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
    åĨįæľī
    -0.08
    æĹłæĦı
    -0.08
    гада
    -0.08
    oo
    -0.08
     somehow
    -0.07
     decltype
    -0.07
    онов
    -0.07
    åĽłæĤ¨çļĦ
    -0.07
    inado
    -0.07
     yyn
    -0.07
    POSITIVE LOGITS
    è¦ģ
    0.09
    åºĶæĮī
    0.09
    è¦ģæĢİä¹Ī
    0.09
    è¦ģæĬĬ
    0.09
    è¦ģæĮīçħ§
    0.09
     Äijá»ĥ
    0.09
    è¦ģåľ¨
    0.09
    åºĶéĩĩçĶ¨
    0.09
    è¦ģ继ç»Ń
    0.09
    è¦ģ对
    0.09
    Activations Density 0.470%

    No Known Activations