© 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. 16231
    Prev
    Next
    INDEX
    Explanations

    equator or equinox

    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
    Ø©
    -0.12
    ness
    -0.10
    翼翼
    -0.09
    ation
    -0.08
    pector
    -0.08
    agger
    -0.08
    åĮªæµħ
    -0.08
    æ¡¥åĮº
    -0.08
    ily
    -0.08
    èĩªæĭħ
    -0.07
    POSITIVE LOGITS
    inox
    0.08
    IgnoreCase
    0.07
    ragen
    0.07
    ropical
    0.07
    -Pacific
    0.07
    opan
    0.07
    ä¸Ģ带
    0.07
    .BorderSize
    0.07
    opat
    0.06
    ÑģÑĤÑĢ
    0.06
    Activations Density 0.003%

    No Known Activations