© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23846
    Prev
    Next
    INDEX
    Explanations

    Price, Total, Vol

    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
    Not in Any Lists

    No Comments

    Negative Logits
    पà¥Ģ
    -0.08
    urr
    -0.08
    太éĥİ
    -0.07
    ä¸įçĦ¶
    -0.07
    æĹłæŃ¢å¢ĥ
    -0.07
     verschieden
    -0.07
    è¿Ľä¿®
    -0.07
     revolving
    -0.07
    utow
    -0.07
    ä¸Ģæĺ¯
    -0.07
    POSITIVE LOGITS
    å¤ĩ注
    0.08
     corresponding
    0.08
    缸åºĶçļĦ
    0.07
     Bucks
    0.07
    对åºĶçļĦ
    0.07
    æĢ¨è¨Ģ
    0.07
    ucing
    0.07
      ↵
    0.06
    rok
    0.06
    ÙĪاد
    0.06
    Activations Density 0.009%

    No Known Activations