© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26811
    Prev
    Next
    INDEX
    Explanations

    fields and code identifiers

    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
    æĺ¥æĿ¥
    -0.09
    inand
    -0.08
    人åijĺåIJįåįķ
    -0.07
    âķij
    -0.07
    elli
    -0.07
    noop
    -0.07
    iative
    -0.07
    Falsy
    -0.07
    æ¼Ķ
    -0.06
    èĬ¹
    -0.06
    POSITIVE LOGITS
    ouer
    0.08
    åĨį
    0.07
    ss
    0.07
    ou
    0.06
    å¼ĢåĬ¨
    0.06
    èĩª
    0.06
    ä¸įæĸŃæĶ¹è¿Ľ
    0.06
    ä¸İç»´æĬ¤
    0.06
    åĨįçĶŁ
    0.06
    ä¸Ĭ大
    0.06
    Activations Density 0.192%

    No Known Activations