© 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. 46088
    Prev
    Next
    INDEX
    Explanations

    when Dou Good Looking Men If All

    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
    erma
    -0.08
    åı¦ä¸Ģè¾¹
    -0.07
    \/\/
    -0.07
     Uncomment
    -0.07
    åı¦ä¸ĢåįĬ
    -0.07
    éģ¿åħįåĩºçİ°
    -0.07
     pess
    -0.07
    ajo
    -0.07
    epak
    -0.06
    Ĥ
    -0.06
    POSITIVE LOGITS
    ĴĪ
    0.08
    æ¿®
    0.08
     erster
    0.07
    ãģªãĤĤãģ®
    0.07
    _first
    0.07
    第ä¸Ģä½į
    0.07
    _modules
    0.07
    ç¯ĩä¸Ģ
    0.07
    illos
    0.06
    第ä¸Ģç¯ĩ
    0.06
    Activations Density 0.221%

    No Known Activations