© 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. 10509
    Prev
    Next
    INDEX
    Explanations

    body or process followed by punctuation

    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
     exp
    -0.07
    åľ¨åĨħçļĦ
    -0.07
    主åĬŀçļĦ
    -0.07
    交æµģä¸İ
    -0.07
    æĬ¥è®¯
    -0.07
    è·¯ä¸İ
    -0.07
    ä¹ĭåIJį
    -0.07
    .dev
    -0.06
    å¡ĺéķĩ
    -0.06
    .Pass
    -0.06
    POSITIVE LOGITS
    erp
    0.07
    اء
    0.07
    ovski
    0.07
    æ¸ħæĻ°åº¦
    0.07
    é¤
    0.06
    ä¸īé«ĺ
    0.06
    èĢĮæĺ¯åĽłä¸º
    0.06
    产æĿĥ
    0.06
    olley
    0.06
    (Unknown
    0.06
    Activations Density 0.001%

    No Known Activations