© 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. 44359
    Prev
    Next
    INDEX
    Explanations

    average, national, and rankings

    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
    akedown
    -0.07
    жаÑĤ
    -0.07
    obil
    -0.07
     schem
    -0.07
    大åĪĩ
    -0.07
    两ç§įæĸ¹å¼ı
    -0.07
    sep
    -0.07
     acting
    -0.07
    éĩįè¦ģä½ľçĶ¨
    -0.07
     пÑĢид
    -0.07
    POSITIVE LOGITS
    çĽ¸å¯¹è¾ĥä½İ
    0.09
    åĿĩåĢ¼
    0.08
    çŃīåľ°åĮº
    0.08
     average
    0.08
     comparisons
    0.08
     statist
    0.08
     ethnic
    0.08
     averages
    0.08
     rankings
    0.08
     comparable
    0.08
    Activations Density 0.224%

    No Known Activations