© 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. 42402
    Prev
    Next
    INDEX
    Explanations

    #import and @ declarations

    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
    wise
    -0.07
     sez
    -0.07
    ypes
    -0.06
    ãĤıãģĸ
    -0.06
    ted
    -0.06
     nev
    -0.06
    tion
    -0.06
     @}
    -0.06
    æĵįä½ľä¸Ĭ
    -0.05
    çIJĨ解为
    -0.05
    POSITIVE LOGITS
    partment
    0.08
    oning
    0.08
    ÂŃs
    0.07
    trias
    0.07
    utow
    0.07
    rian
    0.07
    TickCount
    0.07
    éĺħè¯»æľ¬æĸĩåīį
    0.07
    ailing
    0.07
    öst
    0.07
    Activations Density 0.950%

    No Known Activations