© 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. 6937
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    adini
    -0.09
    åħįè´¹åĴ¨è¯¢
    -0.09
    ä¹ĭçĪ¶
    -0.08
    ÙģÙĦ
    -0.08
    Òº
    -0.08
    lech
    -0.08
    æĪijæĿ¥è¯´
    -0.08
    ussen
    -0.08
    æĥ³å¾ĹåĪ°
    -0.08
    quam
    -0.08
    POSITIVE LOGITS
    æĸ°åĬłåĿ¡
    0.11
    åĬłæĭ¿å¤§
    0.08
    缸è¾ħ缸æĪIJ
    0.07
    åħ¢åħ¢ä¸ļä¸ļ
    0.07
    åĭĩå¾Ģ缴åīį
    0.06
    俱ä¹IJéĥ¨
    0.06
    åħ¶ä¸ŃçļĦ
    0.06
    ัà¸Ļ
    0.06
    éĺ¿æĭī伯
    0.06
     (
    0.05
    Activations Density 0.023%

    No Known Activations