© 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. 56894
    Prev
    Next
    INDEX
    Explanations

    mark other components, territory, or as marked

    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
    à¸Ĺà¹Į
    -0.09
    zehn
    -0.08
    iable
    -0.08
    maal
    -0.08
    ilers
    -0.08
    omon
    -0.07
    iated
    -0.07
    ddy
    -0.07
    -même
    -0.07
    /of
    -0.07
    POSITIVE LOGITS
    edly
    0.11
    eting
    0.11
    ETING
    0.10
    edBy
    0.09
    累累
    0.09
    edList
    0.09
    ings
    0.08
     Zuckerberg
    0.08
    ewing
    0.08
    .parametrize
    0.08
    Activations Density 0.085%

    No Known Activations