© 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. 61890
    Prev
    Next
    INDEX
    Explanations

    true, fields, competition, adequate, honesty, number

    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
    amentos
    -0.08
    æ¡£
    -0.08
    ä¹ĭå¤ļ
    -0.08
     triana
    -0.07
    вÑĮ
    -0.07
    åĶ
    -0.07
    lash
    -0.07
    à§įম
    -0.07
    oeff
    -0.07
    ()._
    -0.07
    POSITIVE LOGITS
    æīįè¡Į
    0.12
    èĩ³å°ijåľ¨
    0.09
    èĩ³å°ijè¦ģ
    0.09
    æīį好
    0.09
    èĩ³å°ij
    0.09
     failing
    0.08
    æľĢ好æĺ¯
    0.08
    åIJ¦åĪĻ
    0.08
    èµ·çłģ
    0.07
    æīį对
    0.07
    Activations Density 0.063%

    No Known Activations