© 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. 47261
    Prev
    Next
    INDEX
    Explanations

    speak or speaks

    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
    ĺ
    -0.10
     perairan
    -0.07
    readcrumbs
    -0.07
    isplay
    -0.07
    swer
    -0.07
    ierung
    -0.07
    webkit
    -0.07
     paperwork
    -0.07
    IMUM
    -0.07
    æĢ§åľ°
    -0.07
    POSITIVE LOGITS
     dá»iji
    0.09
    åĴĮè¡ĮåĬ¨
    0.08
    unication
    0.08
     tắt
    0.07
    ooter
    0.07
    -speaking
    0.07
    icona
    0.07
    举æŃ¢
    0.07
    ÑģÑĤо
    0.07
    Ïĥή
    0.07
    Activations Density 0.066%

    No Known Activations