© 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. 59839
    Prev
    Next
    INDEX
    Explanations

    table rows and dates

    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
    erot
    -0.08
    顾åIJįæĢĿ
    -0.08
    iels
    -0.08
    lian
    -0.07
    amol
    -0.07
    ï¼įï¼įï¼įï¼į
    -0.07
    å½±
    -0.07
    intern
    -0.07
    æľĹ
    -0.07
    ä¸ĢèĪ¬
    -0.07
    POSITIVE LOGITS
    ä¸İä½ľçĶ¨
    0.07
    TRS
    0.07
    दà¥įध
    0.07
    ãģĦãģł
    0.07
    enf
    0.07
    ä¸İæľ¬
    0.07
    åıĬè¦ģæ±Ĥ
    0.06
     typeof
    0.06
    CTS
    0.06
    åı°åīį
    0.06
    Activations Density 0.009%

    No Known Activations