© 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. 25802
    Prev
    Next
    INDEX
    Explanations

    special characters, code, and localization

    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
    ukas
    -0.07
    uggy
    -0.06
    um
    -0.06
    ukan
    -0.06
    anas
    -0.06
    人äºĨ
    -0.06
     appunto
    -0.06
    amma
    -0.06
    K
    -0.06
    Ľ
    -0.06
    POSITIVE LOGITS
    "],"
    0.08
    ertime
    0.08
    ÙĬب
    0.08
    ryn
    0.07
    åľĵ
    0.07
    egie
    0.07
    çīĪæĿĥå½ĴåİŁä½ľèĢħ
    0.07
    atge
    0.07
    ?>>
    0.07
    çŃīçŃī
    0.07
    Activations Density 0.042%

    No Known Activations