© 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. 44744
    Prev
    Next
    INDEX
    Explanations

    /pay or -pay

    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
    idio
    -0.07
    illin
    -0.07
    eler
    -0.06
    boy
    -0.06
    ick
    -0.06
    ptune
    -0.06
    hide
    -0.06
     dear
    -0.06
     enough
    -0.06
    quil
    -0.06
    POSITIVE LOGITS
    Ä«j
    0.08
    awal
    0.08
    /all
    0.08
    åħ¶ä»ĸæĸ¹å¼ı
    0.08
    finite
    0.08
    -pay
    0.07
    ä¹IJä¹IJ
    0.07
    erator
    0.07
    /pay
    0.07
    æŁIJ天
    0.07
    Activations Density 0.003%

    No Known Activations