© 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. 43029
    Prev
    Next
    INDEX
    Explanations

    contrast and exception conjunctions

    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
    é«ĺå¤Ħ
    -0.08
    ä¸įåĪĨ
    -0.07
    éķ¿éĿĴ
    -0.07
    ä¸į好äºĨ
    -0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.07
    áŁĭ
    -0.07
    éľĢè¦ģèĢĥèĻij
    -0.07
    asca
    -0.07
    heid
    -0.06
    embro
    -0.06
    POSITIVE LOGITS
     fortunately
    0.10
     luckily
    0.09
     thankfully
    0.08
    StackTrace
    0.08
    幸
    0.07
    è¿ĺ好
    0.07
    ä¸įèĩ³äºİ
    0.07
    好æŃ¹
    0.07
    åıªè¦ģåľ¨
    0.07
     strangely
    0.07
    Activations Density 0.129%

    No Known Activations