© 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. 47216
    Prev
    Next
    INDEX
    Explanations

    HTML tags with attributes

    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
    æĹłè®ºæĺ¯
    -0.08
     '=
    -0.08
    æīĢ以çİ°åľ¨
    -0.07
    æijĩ
    -0.07
    æĹłè®ºæĺ¯åľ¨
    -0.07
    æijĩæijĩ
    -0.07
    æĹłè®ºåľ¨
    -0.07
    ä¸ĭä¸Ģ级
    -0.07
    鸾
    -0.07
     Tanto
    -0.07
    POSITIVE LOGITS
    çŃīçŃī
    0.10
    ä¹ĭç±»çļĦ
    0.09
    ä¹ĭç±»
    0.08
     etc
    0.08
     gist
    0.07
    åıĪæĪĸèĢħ
    0.07
     usw
    0.07
    åİļ
    0.07
    ombo
    0.07
    stell
    0.06
    Activations Density 0.004%

    No Known Activations