© 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. 58872
    Prev
    Next
    INDEX
    Explanations

    interchangeably, same thing, equivalent, identical

    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
    æ»¡åľ°
    -0.09
    ç¼Ń
    -0.08
    ä½łä»¥ä¸º
    -0.08
    éĥ½ä¸įä¸Ģæł·
    -0.08
    è´§
    -0.07
    _KIND
    -0.07
    è¿Ļåı«
    -0.07
    queo
    -0.07
    è´§åĪ°
    -0.07
    uggle
    -0.07
    POSITIVE LOGITS
    _major
    0.08
    æĥ¹
    0.06
    ij
    0.06
    èĢ½
    0.06
    oi
    0.06
     تÙĤرÙĬب
    0.06
    åºĨ幸
    0.06
     features
    0.06
    ×ķר
    0.06
    cj
    0.06
    Activations Density 0.001%

    No Known Activations