© 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. 21256
    Prev
    Next
    INDEX
    Explanations

    sounds like a promising assessment

    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
    bauer
    -0.09
    åĪ°åºķæľīå¤ļ
    -0.09
    obie
    -0.08
    ermen
    -0.08
     allegedly
    -0.08
    åĪ«å¿ĺäºĨ
    -0.08
    jul
    -0.08
    å¿įåıĹ
    -0.08
    ÑıÑĢ
    -0.07
    uç
    -0.07
    POSITIVE LOGITS
     plausible
    0.08
     promising
    0.08
     olev
    0.08
    æĽ´åĥıæĺ¯
    0.08
    åĥıæĺ¯
    0.07
     Promise
    0.07
     ÙĪÙĥØ£ÙĨ
    0.06
    a
    0.06
     promise
    0.06
     prima
    0.06
    Activations Density 0.057%

    No Known Activations