© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33088
    Prev
    Next
    INDEX
    Explanations

    equivalent to / same as

    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
    äºĭå®ľ
    -0.08
    ä½ľä¸ºä¸ŃåĽ½
    -0.08
    羣æĺ¯ä¸ª
    -0.07
     finalmente
    -0.07
    羣æŃ£å®ŀçİ°
    -0.07
    æī§è¡Įå®ĺ
    -0.07
    atia
    -0.07
    æĺ¯å¦ĤæѤ
    -0.07
    utzen
    -0.07
    æĪIJæŃ£
    -0.07
    POSITIVE LOGITS
     saying
    0.09
    ä»Ģä¹Īåij¢
    0.08
    说
    0.07
     being
    0.07
    åıĺ缸
    0.07
    说è¦ģ
    0.07
     asking
    0.07
    æŀģäºĨ
    0.07
    æĬĬä¸Ģ个
    0.07
     having
    0.07
    Activations Density 0.020%

    No Known Activations