© 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. 59041
    Prev
    Next
    INDEX
    Explanations

    email addresses or code snippets

    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
    ips
    -0.08
    ynd
    -0.07
    æ´»åĬ¨åĨħ容
    -0.07
    .toolbox
    -0.07
    yah
    -0.07
    imen
    -0.07
    yip
    -0.07
    spath
    -0.07
    åľŁå»º
    -0.07
    ilmente
    -0.06
    POSITIVE LOGITS
     scoped
    0.07
     Latest
    0.07
    è¹´
    0.07
    etto
    0.07
    鼼
    0.06
    اک
    0.06
    رة
    0.06
    wort
    0.06
     features
    0.06
    Ready
    0.06
    Activations Density 0.001%

    No Known Activations