© 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. 49729
    Prev
    Next
    INDEX
    Explanations

    CH2 and oxygen containing groups

    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
    æĺ¯æĮīçħ§
    -0.08
    á»Ŀ
    -0.06
    ney
    -0.06
    ä¸įæĬĺä¸įæī£
    -0.06
    _sources
    -0.06
     isNaN
    -0.06
    rien
    -0.06
    antina
    -0.06
    åħ¬å·®
    -0.06
    erre
    -0.06
    POSITIVE LOGITS
    å±±æĻ¯åĮº
    0.08
    ç±į
    0.08
    å±Ģ
    0.07
    è°¢
    0.07
    ç«£
    0.07
    社
    0.07
    ä¸Ģå±Ģ
    0.07
    åİŁæľ¬æĺ¯
    0.07
    pecting
    0.07
    çĶµæ°ĶæľīéĻIJåħ¬åı¸
    0.07
    Activations Density 0.021%

    No Known Activations