© 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. 27544
    Prev
    Next
    INDEX
    Explanations

    carbonyl

    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
    ively
    -0.11
    ings
    -0.09
    ering
    -0.09
    avel
    -0.08
    erman
    -0.08
    OrCreate
    -0.08
    iable
    -0.08
    ered
    -0.08
    iveness
    -0.08
    çĴĢ
    -0.07
    POSITIVE LOGITS
    ehme
    0.08
    人
    0.07
    à¹Į
    0.07
    人æĹł
    0.07
    type
    0.07
    лаÑģ
    0.07
    eine
    0.07
    ÙĬØ©
    0.07
    ption
    0.07
    ி
    0.07
    Activations Density 0.001%

    No Known Activations