© 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. 38309
    Prev
    Next
    INDEX
    Explanations

    as soon 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
    ä¹Łæľīä¸ĢäºĽ
    -0.08
     nonetheless
    -0.07
     Propel
    -0.07
    ä¹Łä¸įä¸Ģå®ļ
    -0.07
    lega
    -0.07
     nevertheless
    -0.07
    责任ç¼ĸè¾ij
    -0.07
    ä¹Łä¸įä¸Ģæł·
    -0.07
    imore
    -0.07
    (nullptr
    -0.07
    POSITIVE LOGITS
    便åı¯
    0.11
    åĵªæĢķ
    0.11
    åıªè¦ģæĺ¯
    0.10
    åıªè¦ģæľī
    0.10
    åĵªæĢķæĺ¯
    0.10
    åıªè¦ģ
    0.10
    è¶³å¤Ł
    0.09
    她便
    0.09
    åıªè¦ģåľ¨
    0.09
    åıªè¦ģä¸Ģ
    0.09
    Activations Density 0.102%

    No Known Activations