© 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. 63326
    Prev
    Next
    INDEX
    Explanations

    Casey, Lennon, Hopper, Irvine

    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
    ä¼ļåijĺåįķä½į
    -0.08
    edy
    -0.07
    缸åħ³åįķä½į
    -0.07
    å®ĺåĵ¡
    -0.07
    åĨį次
    -0.07
    ëĤĺëĿ¼
    -0.07
    æĺ¯ä¸Ģç§į常è§ģçļĦ
    -0.07
    WithDuration
    -0.07
    å®ĺåIJı
    -0.07
    çĿĢå®ŀ
    -0.07
    POSITIVE LOGITS
    åĪĨæĭħ
    0.10
    åĪĨå·¥
    0.09
    æIJŃæ¡£
    0.08
    主导
    0.08
    ä¸ī人
    0.08
    é»ĺå¥ij
    0.08
     partnered
    0.08
    çīµå¤´
    0.08
    ä¸Ģæĭį
    0.08
     shared
    0.08
    Activations Density 0.366%

    No Known Activations