© 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. 10906
    Prev
    Next
    INDEX
    Explanations

    photo or image file names

    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
    äºĨæĪijçļĦ
    -0.07
    _lazy
    -0.06
    l
    -0.06
    _formats
    -0.06
    leh
    -0.06
    άÏģ
    -0.06
    è£Ļ
    -0.06
    åįĸ
    -0.06
    uk
    -0.06
     []
    -0.06
    POSITIVE LOGITS
    _PROVID
    0.09
    æĹ¥åIJİçļĦ
    0.08
    راÙĦ
    0.08
    igts
    0.07
    RunWith
    0.07
    ÐŁÐµÑĢе
    0.07
    FULL
    0.07
     perk
    0.07
    darwin
    0.07
    以å¾Į
    0.07
    Activations Density 0.001%

    No Known Activations