© 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. 49127
    Prev
    Next
    INDEX
    Explanations

    if present then

    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
    æĿ¥æŶ
    -0.08
    鼰
    -0.08
    Submitting
    -0.08
     admittedly
    -0.08
    é¡»çŁ¥
    -0.08
    utures
    -0.08
    /manage
    -0.08
    OptionsMenu
    -0.08
    æĢİä¹ĪåĨĻ
    -0.07
    Inlining
    -0.07
    POSITIVE LOGITS
    ãģĿãģ®ãģ¾ãģ¾
    0.09
     deem
    0.08
     ê·¸ëĮĢë¡ľ
    0.07
    stick
    0.07
     ÑģÑĩиÑĤаеÑĤÑģÑı
    0.07
    继ç»Ń
    0.07
    ä¸ĭä¸ĢæŃ¥
    0.06
     continue
    0.06
     considered
    0.06
    empre
    0.06
    Activations Density 0.051%

    No Known Activations