© 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. 9358
    Prev
    Next
    INDEX
    Explanations

    Cheltenham Festival

    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
    ahari
    -0.08
    æ»ĭ
    -0.07
    .nlm
    -0.07
     Ful
    -0.07
     Mellon
    -0.07
    ()):
    -0.07
    çīĪæĿĥå½ĴåİŁä½ľèĢħ
    -0.07
    æĹłåIJį
    -0.07
    etro
    -0.07
    PLE
    -0.07
    POSITIVE LOGITS
    berge
    0.07
    æŶä¸ĭ
    0.07
    ä½łä¸Ģ个
    0.06
    æľĢçĪ±
    0.06
    代
    0.06
    å§Ĩ
    0.06
    enburg
    0.06
    anko
    0.06
    æĺ¯ä¸Ģ个éĿŀ常
    0.06
    bard
    0.06
    Activations Density 0.001%

    No Known Activations