© 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. 4616
    Prev
    Next
    INDEX
    Explanations

    either/or choices

    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
    uling
    -0.07
    汪æ´ĭ
    -0.07
    ÑĢое
    -0.07
    rios
    -0.07
    orro
    -0.06
    agaan
    -0.06
    ryo
    -0.06
    usen
    -0.06
    æĻ¨
    -0.06
    æ¤İ
    -0.06
    POSITIVE LOGITS
     either
    0.10
     somewhere
    0.09
    /or
    0.09
    either
    0.09
    è¦ģä¹Ī
    0.08
    ãģĤãģŁãĤĬ
    0.08
     Either
    0.08
     sometime
    0.08
    Either
    0.08
    æłĭæ¢ģ
    0.08
    Activations Density 0.025%

    No Known Activations