© 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. 10094
    Prev
    Next
    INDEX
    Explanations

    pickle and plist

    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
     اÙĦÙĨÙĤ
    -0.07
     hub
    -0.06
    èľ
    -0.06
    æ±
    -0.06
    漫
    -0.06
    ocker
    -0.06
    ä¹ĥ
    -0.06
    in
    -0.06
    able
    -0.06
    åħ±äº§åħļ
    -0.06
    POSITIVE LOGITS
    åIJŀ
    0.09
    orate
    0.08
    Mui
    0.08
    ills
    0.08
    FTA
    0.08
    erule
    0.08
    oster
    0.08
    ISM
    0.08
    uppy
    0.08
    ½Ķ
    0.07
    Activations Density 0.001%

    No Known Activations