© 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. 56451
    Prev
    Next
    INDEX
    Explanations

    sorting or ordering

    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
     parfa
    -0.08
    اÙĨد
    -0.07
    让æĪijçļĦ
    -0.07
     Moj
    -0.07
    anj
    -0.07
    enf
    -0.07
    寸
    -0.07
    åħ·å¤ĩèī¯å¥½çļĦ
    -0.07
    ä¸įåı¯åıĬ
    -0.07
    otar
    -0.07
    POSITIVE LOGITS
    永康
    0.07
    åijĺ
    0.07
    ipro
    0.07
    uran
    0.07
    åĢĴ
    0.06
    åıįåIJij
    0.06
    piegel
    0.06
    åIJĪ并
    0.06
    pp
    0.06
    ça
    0.06
    Activations Density 0.115%

    No Known Activations