© 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. 4759
    Prev
    Next
    INDEX
    Explanations

    opposite directions, unequal, symmetric

    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
    ICA
    -0.07
     íĦ
    -0.07
    è¿ĩ渡
    -0.07
    çľĭäºĨ
    -0.07
    toi
    -0.06
     EUROP
    -0.06
    ัย
    -0.06
    stur
    -0.06
    渡åı£
    -0.06
    descriptor
    -0.06
    POSITIVE LOGITS
    两边çļĦ
    0.08
     unequal
    0.07
    Equal
    0.07
    åĬĪ
    0.07
     symmetric
    0.07
     sym
    0.07
    æ´»åĬ¨æĸ¹æ¡Ī
    0.07
    两侧
    0.07
    RTL
    0.07
    æĹ©æĻļ
    0.07
    Activations Density 0.002%

    No Known Activations