© 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. 34793
    Prev
    Next
    INDEX
    Explanations

    either/or constructions

    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
    gili
    -0.09
    edy
    -0.08
    viv
    -0.08
    å¤ļæľī
    -0.08
    evers
    -0.08
    ìłľëĬĶ
    -0.08
    ammans
    -0.07
    æłĩåħµ
    -0.07
    åĪĿè§ģ
    -0.07
    igham
    -0.07
    POSITIVE LOGITS
     either
    0.08
    è¦ģä¹Ī
    0.07
    æĪļ
    0.06
     либо
    0.06
    è¦ģä¹Īæĺ¯
    0.06
     uses
    0.06
    ieurs
    0.06
     entweder
    0.06
    é¥Ń
    0.06
    ubi
    0.06
    Activations Density 0.042%

    No Known Activations