© 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. 37557
    Prev
    Next
    INDEX
    Explanations

    section identifiers

    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
    endale
    -0.07
     instead
    -0.06
    ä¸ŃåĽ½äººæ°ij解æĶ¾åĨĽ
    -0.05
    碧绿
    -0.05
    aje
    -0.05
    æıIJåıĸçī©
    -0.05
    hors
    -0.05
    endig
    -0.05
    verk
    -0.05
    â
    -0.05
    POSITIVE LOGITS
    è¦ģä¸įçĦ¶
    0.08
     bedan
    0.08
    åĴĮæĦıä¹ī
    0.08
    <|box_end|>
    0.08
    baugh
    0.08
    оеди
    0.08
    ppi
    0.08
    æĸ°ç½ij
    0.07
    oppen
    0.07
    uye
    0.07
    Activations Density 0.191%

    No Known Activations