© 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. 19023
    Prev
    Next
    INDEX
    Explanations

    offers, existence, forthcoming

    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
    INET
    -0.06
     argued
    -0.06
    æħĭ
    -0.06
    èĸĩ
    -0.06
    +"]
    -0.06
    hci
    -0.06
    _UT
    -0.06
    çıij
    -0.05
    æĪij建议
    -0.05
    keb
    -0.05
    POSITIVE LOGITS
     ÙĪØ£ÙĨÙĩ
    0.10
     forthcoming
    0.08
    åijĬè¯īèĩªå·±
    0.08
    à¸Ĥà¸Ńà¸ĩà¸ķà¸Ļ
    0.08
    åĽŃè·¯
    0.08
    çļĦéĩįè¦ģæĢ§åĴĮ
    0.08
     ÑıкобÑĭ
    0.08
    以åıĬå¦Ĥä½ķ
    0.08
     impending
    0.08
     мол
    0.08
    Activations Density 0.357%

    No Known Activations