© 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. 4697
    Prev
    Next
    INDEX
    Explanations

    clinical trial or study name

    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
    é¢Ħç§ij
    -0.08
    大ä¼ļåłĤ
    -0.07
    æ£Ģå¯Łéķ¿
    -0.06
    çĶŁçĶŁ
    -0.06
    resident
    -0.06
     glass
    -0.06
    ä»İè¿Ļ个
    -0.06
    ä¼ļå±ķä¸Ńå¿ĥ
    -0.06
     Fres
    -0.06
    icens
    -0.06
    POSITIVE LOGITS
    uers
    0.09
    /disc
    0.07
     exceptional
    0.07
    ùm
    0.07
    æŀļ举
    0.07
    emi
    0.07
    ä¾ĭå¤ĸ
    0.07
    onis
    0.07
    å«Įçĸij
    0.07
    ä¸įåĭķ
    0.07
    Activations Density 0.008%

    No Known Activations