© 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. 28979
    Prev
    Next
    INDEX
    Explanations

    formed from or derived from

    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
    geist
    -0.07
    æİĮ
    -0.07
    æĹ¥èµ·èĩ³
    -0.06
    æĦŁæĥ³
    -0.06
    nel
    -0.06
    å¸ĥæĸ¯
    -0.06
    yton
    -0.06
    ìĿ¼ê¹Įì§Ģ
    -0.06
    à¹īม
    -0.06
    ạn
    -0.06
    POSITIVE LOGITS
    มาà¸Īาà¸ģ
    0.10
    缴æİ¥ä»İ
    0.09
    ä»İæĹł
    0.09
     from
    0.09
    å·¥ä½ľéľĢè¦ģ
    0.09
    æĿ¥ä¹ĭ
    0.08
     пÑĥÑĤем
    0.08
    ä»İä½ķ
    0.08
    æĺ¯ä»İ
    0.08
     previous
    0.08
    Activations Density 0.313%

    No Known Activations