© 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. 16428
    Prev
    Next
    INDEX
    Explanations

    comparison or counting

    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
    äºĶä¸Ģ
    -0.07
    ÃŃv
    -0.07
    æĴĩ
    -0.07
    å¦ĤåĽł
    -0.06
    ç¿ĺ
    -0.06
    çĶ±çľģ
    -0.06
     denomin
    -0.06
    åį³ä¾¿å¦ĤæѤ
    -0.06
     least
    -0.06
    å¾·å°Ķ
    -0.06
    POSITIVE LOGITS
     compared
    0.14
     compare
    0.14
     compares
    0.13
    compare
    0.13
    æ¯Ķ对
    0.12
     Compare
    0.12
     ÙħÙĤارÙĨØ©
    0.12
     Compared
    0.11
    Compare
    0.11
    æĺ¯åIJ¦ç¬¦åIJĪ
    0.11
    Activations Density 0.209%

    No Known Activations