© 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. 578
    Prev
    Next
    INDEX
    Explanations

    symmetric duplicate or half

    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
    æŃ¤åľ°
    -0.08
    usser
    -0.07
    Pros
    -0.07
    天ä¹ĭ
    -0.07
    饿äºĨ
    -0.07
    綿
    -0.07
     schad
    -0.07
    æľĢæł¹æľ¬
    -0.07
    çĿĢæĢ¥
    -0.07
    عÙĨ
    -0.07
    POSITIVE LOGITS
    对称
    0.09
     symmetry
    0.09
     Sym
    0.08
    åįķè¾¹
    0.08
    Dup
    0.08
    ä¸į对称
    0.08
    ymmetric
    0.08
     symmetric
    0.08
    Duplicate
    0.08
     полов
    0.08
    Activations Density 0.007%

    No Known Activations