© 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. 22462
    Prev
    Next
    INDEX
    Explanations

    group lifecycle policies, apps, calendars, problems

    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
    thon
    -0.07
    arik
    -0.07
    verture
    -0.07
    iski
    -0.07
    ton
    -0.07
    burgh
    -0.07
    aran
    -0.07
    æ®ĸ
    -0.07
    .Suppress
    -0.06
    .Dictionary
    -0.06
    POSITIVE LOGITS
    æĺķ
    0.07
     named
    0.07
     created
    0.07
     registered
    0.07
     eid
    0.07
    æĪĸå¤ļ个
    0.07
    æĺ¨æĹ¥
    0.07
    æīĢå±ŀ
    0.06
    ID
    0.06
    _id
    0.06
    Activations Density 0.509%

    No Known Activations