© 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. 58065
    Prev
    Next
    INDEX
    Explanations

    methods and protocols

    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
    æĸ½å·¥è¿ĩç¨ĭä¸Ń
    -0.08
    Seat
    -0.08
    碰碰
    -0.08
    nud
    -0.07
    å°ıåŃ©
    -0.07
    æľªå®Į
    -0.07
     اÙĦÙħد
    -0.07
    loys
    -0.07
    åı¼
    -0.07
    çħŀ
    -0.07
    POSITIVE LOGITS
    è¯ķåīĤ
    0.10
     laboratory
    0.10
    èĢĹæĿIJ
    0.10
     assay
    0.10
     assays
    0.09
     laboratories
    0.09
    è¯ķåīĤçĽĴ
    0.09
    å®ŀéªĮ室
    0.09
     researcher
    0.09
    é«ĺéĢļ
    0.09
    Activations Density 0.277%

    No Known Activations