© 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. 27234
    Prev
    Next
    INDEX
    Explanations

    cyber event, gear units, Hall effect, drill pipe, retail center, transmission system

    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
    å¸ĮæľĽå¯¹å¤§å®¶
    -0.07
    verso
    -0.07
    ajan
    -0.06
    ä¹ŁåĪ«
    -0.06
    versch
    -0.06
    åĪ¥
    -0.06
    chnitt
    -0.06
    交æĺĵç³»ç»Ł
    -0.06
    å¤ĩæ¡Īåı·
    -0.06
     timetable
    -0.06
    POSITIVE LOGITS
     demais
    0.07
    /../
    0.07
    æĪIJäºĨä¸Ģ个
    0.07
     legislation
    0.07
    æľºæŀĦæĶ¹éĿ©
    0.07
    è¿Ļæł·ä¸Ģ个
    0.07
    oris
    0.07
    è¿Ļæł·çļĦä¸Ģ个
    0.07
    çļĦä¸Ģ个
    0.06
    åIJĮåѦéĥ½
    0.06
    Activations Density 2.167%

    No Known Activations