© 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. 25491
    Prev
    Next
    INDEX
    Explanations

    covalent / covalently

    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
    stands
    -0.07
     ÑĢаÑģÑģмоÑĤÑĢениÑı
    -0.06
    porti
    -0.06
    occhi
    -0.06
    quo
    -0.06
    ÙĪØ¡
    -0.06
    رج
    -0.06
    é«ĺåİŁ
    -0.06
    atcher
    -0.06
    lining
    -0.06
    POSITIVE LOGITS
    izable
    0.12
    ÙĬØ©
    0.10
    ekar
    0.09
    ariant
    0.08
    ety
    0.08
    ÄĻb
    0.08
    isable
    0.08
    ized
    0.08
    -elect
    0.08
    ently
    0.08
    Activations Density 0.003%

    No Known Activations