© 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. 50617
    Prev
    Next
    INDEX
    Explanations

    style comments

    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
    å¹´ä¹ĭåIJİ
    -0.08
    afa
    -0.08
    å¼Ĥ
    -0.08
    æįŀ
    -0.07
    ÏĦÏģο
    -0.07
    erien
    -0.07
     recruits
    -0.07
    å·¢
    -0.07
    arez
    -0.07
    ugg
    -0.07
    POSITIVE LOGITS
    usses
    0.07
    éĢļè¡Įè¯ģ
    0.06
     meticulous
    0.06
    è°¨
    0.06
    .annotations
    0.06
    æĸ¹æ³ķä¸İ
    0.06
    ä¸įè¦ģ
    0.06
    对æīĢ
    0.06
     Pes
    0.06
    ="$(
    0.06
    Activations Density 0.003%

    No Known Activations