© 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. 30698
    Prev
    Next
    INDEX
    Explanations

    perhaps, maybe, or uncertainty

    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
     typically
    -0.08
     usually
    -0.08
    éĢļ常
    -0.08
    typically
    -0.08
    åĩłä¹İ
    -0.07
    宦
    -0.07
    éĢļ常ä¼ļ
    -0.07
    éĢļ常æĺ¯
    -0.07
    usually
    -0.07
    çŁ£
    -0.07
    POSITIVE LOGITS
     somehow
    0.15
    æŁIJç§į
    0.15
     perhaps
    0.14
     maybe
    0.14
    ä¹Łè®¸
    0.13
     Maybe
    0.13
    perhaps
    0.13
    åıĪæĪĸèĢħ
    0.13
     Perhaps
    0.12
    ä¹Łè®¸æĺ¯
    0.12
    Activations Density 0.150%

    No Known Activations