© 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. 58871
    Prev
    Next
    INDEX
    Explanations

    material states

    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
     âĢ¦
    -0.06
    oker
    -0.06
    instead
    -0.06
    ç©´
    -0.06
    won
    -0.06
    ons
    -0.06
     r
    -0.06
    åįī
    -0.05
    çŀ³
    -0.05
    âĢ¦
    -0.05
    POSITIVE LOGITS
    æĪĸåħ¶ä»ĸ
    0.16
    æĪĸåħ¶å®ĥ
    0.13
    æĪĸèĢħåħ¶ä»ĸ
    0.13
    åıĬåħ¶ä»ĸ
    0.12
    åĴĮåħ¶ä»ĸ
    0.12
    以åıĬåħ¶ä»ĸ
    0.10
    åıĬåħ¶å®ĥ
    0.10
    åĴĮåħ¶å®ĥ
    0.10
    èĪĩåħ¶ä»ĸ
    0.10
     ÙĪغÙĬرÙĩا
    0.10
    Activations Density 0.362%

    No Known Activations