© 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. 34622
    Prev
    Next
    INDEX
    Explanations

    concepts and context

    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
     reportedly
    -0.08
     certainly
    -0.08
     unfortunately
    -0.07
    èµĦæĸĻæĺ¾ç¤º
    -0.07
     typically
    -0.06
    Ùijا
    -0.06
    说è¦ģ
    -0.06
    obra
    -0.06
    äºĽä»Ģä¹Ī
    -0.06
     let
    -0.06
    POSITIVE LOGITS
     sebagai
    0.11
    æ¯Ķä½ľ
    0.11
     بأÙĨÙĩ
    0.11
     بأÙĨÙĩا
    0.11
     à¹Ħวà¹ī
    0.10
    ä½ľä¸ºä¸Ģ个
    0.10
    ä¹Łçº³
    0.09
     jako
    0.09
     Sebagai
    0.09
    å½ĵä½ľ
    0.09
    Activations Density 0.094%

    No Known Activations