© 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. 23967
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives and adverbs

    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
    æĢ§å¼º
    -0.08
     Lampe
    -0.08
    æŀģäºĨ
    -0.08
    æľĢå°ı
    -0.07
    æ®Ĭ
    -0.07
    èĩ³å°ijæľī
    -0.07
     furthermore
    -0.07
    æĽ´è¿Ľä¸ĢæŃ¥
    -0.07
    ׾×ĺ
    -0.07
    inges
    -0.07
    POSITIVE LOGITS
     slightly
    0.13
    çķ¥æľī
    0.12
    çķ¥
    0.12
    çķ¥å¾®
    0.11
     légèrement
    0.10
     nieco
    0.09
    à¹Ģลà¹ĩà¸ģà¸Ļà¹īà¸Ńย
    0.09
     ligeramente
    0.09
    ç¨įå¾®
    0.09
     leggermente
    0.09
    Activations Density 0.054%

    No Known Activations