© 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. 9505
    Prev
    Next
    INDEX
    Explanations

    telephone interview or email

    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
    etton
    -0.08
    Chooser
    -0.08
    ä¸įäºĨå¤ļä¹ħ
    -0.08
    æģŃåĸľä½ł
    -0.08
    交èŃ¦å¤§éĺŁ
    -0.08
    iop
    -0.07
    说ä¸įå®ļ
    -0.07
    è¿Ļä¼ļåĦ¿
    -0.07
    大家éĥ½çŁ¥éģĵ
    -0.07
     maintenant
    -0.07
    POSITIVE LOGITS
     interviewed
    0.09
    sur
    0.08
     tested
    0.08
    è°ĥçłĶ
    0.08
    è°ĥæŁ¥åıijçİ°
    0.08
    æŁ¥éĺħ
    0.07
     interviews
    0.07
    æĺ¯æĪij
    0.07
    _dur
    0.07
    è°ĥæŁ¥ä¸Ń
    0.07
    Activations Density 1.545%

    No Known Activations