© 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. 44407
    Prev
    Next
    INDEX
    Explanations

    places for where

    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
    оÑħо
    -0.08
    æĮĩçĿĢ
    -0.07
     Sla
    -0.07
    ê·¹
    -0.07
    å°½å¿ĥå°½åĬĽ
    -0.07
    产äºİ
    -0.07
    Ùħد
    -0.07
    æĪIJ为ä¸Ģç§į
    -0.07
    åĭĺ
    -0.07
    æĺ¯ä¸Ģ项
    -0.07
    POSITIVE LOGITS
     where
    0.15
     où
    0.12
    where
    0.12
     waarop
    0.12
    Where
    0.11
     donde
    0.11
     dimana
    0.11
     wherein
    0.10
     Where
    0.10
     waar
    0.10
    Activations Density 0.250%

    No Known Activations