© 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. 20326
    Prev
    Next
    INDEX
    Explanations

    nonvolatile

    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
    _idxs
    -0.08
    以ä¸ĭåĨħ容
    -0.08
    APH
    -0.08
    atori
    -0.08
    indre
    -0.08
    undry
    -0.08
    SSIP
    -0.08
    çļĦåIJĦ项
    -0.08
     ArgumentNullException
    -0.07
    åIJĦæĸ¹éĿ¢
    -0.07
    POSITIVE LOGITS
    åı¯è°ĵ
    0.08
     بذÙĦÙĥ
    0.08
    åIJįåī¯åħ¶å®ŀçļĦ
    0.08
     truly
    0.07
    ä»İè¿Ļ个
    0.07
     ë§Īì¹ĺ
    0.07
    ä¹Łç§°ä¸º
    0.07
    羣æŃ£æĦıä¹īä¸ĬçļĦ
    0.07
    ä¹Łåı«
    0.06
    ä»¿ä½Ľ
    0.06
    Activations Density 0.192%

    No Known Activations