© 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. 56011
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and questions

    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
    iega
    -0.08
    ()',
    -0.08
    ()",
    -0.08
    alba
    -0.08
    erber
    -0.07
    zem
    -0.07
    æĽ´æĸ°äºİ
    -0.07
    acen
    -0.07
    ...",
    -0.07
    ynet
    -0.07
    POSITIVE LOGITS
    ?.
    0.08
    )?
    0.07
    ï¼Ł
    0.07
    angu
    0.06
     ?
    0.06
    ?
    0.06
    ?:
    0.06
    ä¸ĭè§Ĵ
    0.06
    ogle
    0.06
    ness
    0.06
    Activations Density 0.069%

    No Known Activations