© 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. 45569
    Prev
    Next
    INDEX
    Explanations

    examples and especially

    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
    à¹Īวà¸ĩ
    -0.08
    ieber
    -0.08
    ä»·æł¼åĴĮ
    -0.08
    unsch
    -0.08
    mien
    -0.07
    lieb
    -0.07
    Ỽ
    -0.07
    ude
    -0.07
    欢è¿İåħ³æ³¨
    -0.07
    Separated
    -0.07
    POSITIVE LOGITS
    ä¾ĭå¦Ĥ
    0.08
    çļĦåŃĺåľ¨
    0.07
     examples
    0.07
    诸å¦Ĥ
    0.07
    ä¾ĭãģĪãģ°
    0.07
    æ¯Ķå¦Ĥ
    0.06
    ±
    0.06
     Examples
    0.06
    å°¤åħ¶æĺ¯
    0.06
     especially
    0.06
    Activations Density 0.002%

    No Known Activations