© 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. 21058
    Prev
    Next
    INDEX
    Explanations

    of [noun]

    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
    å¿«ä¹IJçļĦ
    -0.10
    幸ç¦ıçļĦ
    -0.09
    ¬ģ
    -0.08
    æĦīå¿«çļĦ
    -0.07
    feder
    -0.07
    eson
    -0.07
    éļ¾åħ³
    -0.07
    ç²¾ç¥ŀä¸Ĭ
    -0.07
    欢快çļĦ
    -0.07
    èī°éļ¾çļĦ
    -0.07
    POSITIVE LOGITS
    perse
    0.08
    å®īåħ¨åĴĮ
    0.08
     forb
    0.07
     determination
    0.07
     оÑģмоÑĤÑĢ
    0.07
     caution
    0.07
    å¾
    0.07
     discretion
    0.06
     hope
    0.06
    .preventDefault
    0.06
    Activations Density 0.362%

    No Known Activations