© 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. 40665
    Prev
    Next
    INDEX
    Explanations

    Lisk account

    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
    笼
    -0.07
    åĿ¡
    -0.06
    nest
    -0.06
    çĭŃ
    -0.06
    åĭº
    -0.06
    onet
    -0.06
    ehr
    -0.06
    sville
    -0.06
    åŀ«
    -0.06
    ä¸įåģļ
    -0.06
    POSITIVE LOGITS
    ibilit
    0.08
    åĪ©çī©
    0.08
    igger
    0.08
    çĴ¨
    0.07
    Toe
    0.07
    hoto
    0.07
    roe
    0.07
    åĪ©çļĦ
    0.07
    acement
    0.07
    ldr
    0.07
    Activations Density 0.003%

    No Known Activations