© 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. 58652
    Prev
    Next
    INDEX
    Explanations

    sequence followed by punctuation or *a/*k

    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
    æ¯ĵ
    -0.08
    æĹħ
    -0.07
    åĪĿè¯ķ
    -0.07
    åĪĿæľŁ
    -0.07
    ç²Ĺç»Ĩ
    -0.07
    æĹ©æľŁ
    -0.06
    åĮº
    -0.06
    lis
    -0.06
    æĹ©æľŁçļĦ
    -0.06
    ãĢģ
    -0.06
    POSITIVE LOGITS
    è²ī
    0.08
    ÐijÐļ
    0.08
    奪
    0.08
    adet
    0.08
    åħĦ妹
    0.07
     appunto
    0.07
    åĪ°æĿ¥çļĦ
    0.07
    æ¦Ħ
    0.07
    ÏģιÏĥ
    0.07
    éľ¹éĽ³
    0.07
    Activations Density 0.006%

    No Known Activations