© 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. 7108
    Prev
    Next
    INDEX
    Explanations

    location and significance

    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
    ä½Ĩæĺ¯åĽłä¸º
    -0.08
    uve
    -0.08
    è§Ĩç½ij
    -0.07
    åīį款
    -0.07
    kite
    -0.07
    uppe
    -0.07
    feeds
    -0.07
    cus
    -0.07
    山头
    -0.07
    สัà¸į
    -0.07
    POSITIVE LOGITS
    以åıĬå¦Ĥä½ķ
    0.10
     ÙĪÙĥÙĬÙģ
    0.09
    åħ·ä½ĵåĨħ容
    0.08
    çļĦåħ·ä½ĵ
    0.08
    çļĦ详ç»Ĩ
    0.08
    mere
    0.08
     подÑĢобно
    0.07
    çļĦåħ·ä½ĵæĥħåĨµ
    0.07
    ird
    0.07
    own
    0.07
    Activations Density 0.369%

    No Known Activations