© 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. 3622
    Prev
    Next
    INDEX
    Explanations

    product or brand 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
     \
    -0.07
    èĵ¦
    -0.06
    fcn
    -0.06
    ä¹Ŀ游
    -0.06
    mbH
    -0.06
    åı¯ä¸º
    -0.06
    é£Łæ¬²ä¸įæĮ¯
    -0.06
    åįİå¾ĭ
    -0.06
    æīĢè¿°çļĦ
    -0.06
    igu
    -0.06
    POSITIVE LOGITS
    çļĦéĤ£ä¸ª
    0.11
    ä»Ģä¹ĪçļĦ
    0.10
    æĪĸèĢħæĺ¯
    0.09
     freaking
    0.09
    çļĦéĤ£ç§į
    0.08
    <|box_end|>
    0.08
    *****
    0.08
    whatever
    0.08
     kinda
    0.08
    endorf
    0.08
    Activations Density 2.655%

    No Known Activations