© 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. 44702
    Prev
    Next
    INDEX
    Explanations

    numbers followed by other numbers or words

    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
    sup
    -0.06
    EGO
    -0.06
    åįģ足
    -0.06
    миÑı
    -0.06
    毫
    -0.06
    à¤ĵà¤Ĥ
    -0.06
    å°±è¿Ļæł·
    -0.06
    arts
    -0.06
    primir
    -0.05
    *
    -0.05
    POSITIVE LOGITS
    sterol
    0.09
    çī¹æľĹ
    0.08
     **ãĢĮ
    0.08
    è¢«ä¾ĽåºĶåķĨ
    0.08
    ué
    0.08
    uš
    0.07
     **âĢŀ
    0.07
    åŃ¦ä»¥èĩ´
    0.07
    eref
    0.07
     Seas
    0.07
    Activations Density 0.118%

    No Known Activations