© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2493
    Prev
    Next
    INDEX
    Explanations

    -carbonyl-

    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
    estad
    -0.08
    èIJĮèĬ½
    -0.07
    çĴĢ
    -0.07
    ç²Ĺç²®
    -0.07
    çŀ³
    -0.07
    wijk
    -0.07
     random
    -0.07
    éģ¿åŃķ
    -0.07
    бол
    -0.07
    saf
    -0.07
    POSITIVE LOGITS
    licht
    0.09
    åŃ£
    0.08
    angled
    0.08
    amide
    0.08
    æŃ»ç¥ŀ
    0.07
    StateChanged
    0.07
    å¹³æ¹ĸ
    0.07
    levator
    0.07
    alts
    0.06
    èĤĿçĹħ
    0.06
    Activations Density 0.009%

    No Known Activations