© 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. 20490
    Prev
    Next
    INDEX
    Explanations

    search for substrings or parts

    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
    说æĺİ
    -0.07
    çģ°
    -0.06
    ette
    -0.06
    ÑĢави
    -0.06
    åħģ
    -0.06
    æīĭå¿ĥ
    -0.06
    说æĺİäºĨ
    -0.06
     conserv
    -0.06
    æĬĬæīĭ
    -0.06
     beij
    -0.05
    POSITIVE LOGITS
    ongyang
    0.11
    Anywhere
    0.09
    IndexOf
    0.08
    oral
    0.08
    æ¯Ķåݻ年åIJĮæľŁ
    0.08
    atap
    0.07
    éĤ£ä¹Łæĺ¯
    0.07
     Propel
    0.07
    碧波
    0.07
    Tahoma
    0.07
    Activations Density 0.004%

    No Known Activations