© 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. 29374
    Prev
    Next
    INDEX
    Explanations

    HTML/CSS stylesheet links

    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
    åħį费订éĺħ
    -0.07
    å°ıåĮº
    -0.07
    æķĻåħ·
    -0.07
    èµ·æĭį
    -0.06
     autobio
    -0.06
    avanaugh
    -0.06
    åĪĹ举
    -0.06
     **:**
    -0.06
    unda
    -0.06
    èµ·
    -0.06
    POSITIVE LOGITS
     stylesheet
    0.09
     pageTitle
    0.08
     STATIC
    0.08
     currentPage
    0.07
    না
    0.07
    midd
    0.07
    å¥ĭè¿Ľ
    0.07
    NavBar
    0.07
     дÑĥÑħ
    0.07
    бÑĢан
    0.07
    Activations Density 0.372%

    No Known Activations