© 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. 33519
    Prev
    Next
    INDEX
    Explanations

    integral notation

    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
    edException
    -0.07
    åIJİèĩ³
    -0.06
    /or
    -0.06
    åĮ»çĶŁçļĦæĮĩ导ä¸ĭ
    -0.06
    uvi
    -0.06
    ukan
    -0.06
    çļĦç¼ĺæķħ
    -0.06
    اÙĨØ´
    -0.06
    stype
    -0.06
    ãģĹãģ¶
    -0.06
    POSITIVE LOGITS
    arth
    0.08
    æĪijä¸ĢçĽ´åľ¨
    0.08
    çļĦéĥ½æĺ¯
    0.07
     Giunta
    0.07
    ovar
    0.07
    ä¹İåħ¶
    0.07
    andong
    0.07
     κάÏĦι
    0.07
    åľ¨åı°
    0.07
    gern
    0.07
    Activations Density 0.025%

    No Known Activations