© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8478
    Prev
    Next
    INDEX
    Explanations

    code increment operators

    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
    azzi
    -0.10
    åĦĺ
    -0.07
    лиÑģÑĤ
    -0.07
    快车
    -0.07
    æĺ±
    -0.07
    thro
    -0.07
    åĩ¯è¿ª
    -0.07
    Ø·ÙĬب
    -0.07
    erable
    -0.07
     Calder
    -0.07
    POSITIVE LOGITS
     ums
    0.07
    å¢ŀåĩı
    0.07
    KeyDown
    0.07
    æĽ²
    0.07
    åħ¶èº«
    0.07
    actor
    0.06
    oud
    0.06
    (if
    0.06
    å°±æĺ¯äºĨ
    0.06
    abal
    0.06
    Activations Density 0.024%

    No Known Activations