© 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. 44711
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    ajok
    -0.07
    ád
    -0.07
    enor
    -0.07
    oin
    -0.07
    ä¼Łå¤§çļĦ
    -0.07
    ÑĤии
    -0.07
    çľĭæ³ķ
    -0.07
    orna
    -0.07
    è¿İéļ¾
    -0.07
    eger
    -0.06
    POSITIVE LOGITS
     rapi
    0.07
    rou
    0.07
    SSI
    0.07
    IVID
    0.07
    ç¥ł
    0.06
    åľ¨å¸Ĥ
    0.06
    raga
    0.06
    ä»»ä½ķåªĴä½ĵ
    0.06
     Spur
    0.06
    æľĶ
    0.06
    Activations Density 0.143%

    No Known Activations