© 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. 14677
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code

    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
    s
    -0.09
    sit
    -0.08
    oja
    -0.07
    "
    -0.06
    ¯
    -0.06
    ...
    -0.06
    parable
    -0.06
    /
    -0.06
    '
    -0.06
    ye
    -0.06
    POSITIVE LOGITS
    etheless
    0.09
    emsp
    0.09
    jenigen
    0.09
    ä¿¡æģ¯ä¸¾æĬ¥
    0.09
    embe
    0.09
    æĺĵè´Ń
    0.08
    нÑij
    0.08
    à³įದ
    0.08
    umentos
    0.08
    åıĪå¦Ĥ
    0.08
    Activations Density 0.011%

    No Known Activations