© 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. 20907
    Prev
    Next
    INDEX
    Explanations

    in a manner/way

    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
    å¤§å®¶åľ¨
    -0.09
    หà¸Ļึà¹Īà¸ĩà¹ĥà¸Ļ
    -0.09
     вÑģÑĤÑĢеÑĩе
    -0.08
     внеÑģении
    -0.08
    åľ¨è®¾è®¡
    -0.07
    æĤ£èĢħåľ¨
    -0.07
    åľ¨éĢīæĭ©
    -0.07
      ↵    ↵
    -0.07
    æķĻå¸Īåľ¨
    -0.07
    à¸ģัà¸Ļà¹ĥà¸Ļ
    -0.07
    POSITIVE LOGITS
     midst
    0.11
     accordance
    0.10
    /out
    0.10
    lighet
    0.09
     vicinity
    0.09
     manner
    0.08
     Weise
    0.08
    /of
    0.08
     vitro
    0.08
     context
    0.07
    Activations Density 0.242%

    No Known Activations