© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59088
    Prev
    Next
    INDEX
    Explanations

    during time periods or events

    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
    Negative Logits
    etic
    -0.08
    以赴
    -0.07
    antal
    -0.07
    elligen
    -0.07
    를
    -0.07
    enticated
    -0.07
    åħĪå¾Ĺ
    -0.07
    ãģ®ãģ§ãģĤãĤĭ
    -0.07
    ellers
    -0.07
    presso
    -0.07
    POSITIVE LOGITS
    dessen
    0.14
     διάÏģκεια
    0.11
    heen
    0.10
     ÙĪبعد
    0.10
    abouts
    0.10
     lesquels
    0.09
    е
    0.09
    /by
    0.08
    Ø©
    0.08
    /on
    0.08
    Activations Density 0.102%

    No Known Activations