© 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. 26213
    Prev
    Next
    INDEX
    Explanations

    /EG B type

    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
    åįĥéĩĮ
    -0.08
    Ñĥз
    -0.07
    éľĢçĶ¨
    -0.07
    -results
    -0.07
    顺åĬ¿
    -0.07
    ÙĬاÙĨ
    -0.07
    aks
    -0.07
    saan
    -0.07
    urger
    -0.06
    æľĢåIJİæĺ¯
    -0.06
    POSITIVE LOGITS
    éķ¿ç©º
    0.07
    اÙħÙĬ
    0.07
    代åıij
    0.07
    åģ¥ç¾İ
    0.06
    æī©å±ķèµĦæĸĻ
    0.06
    Mahon
    0.06
    ÏģÏİ
    0.06
    ncy
    0.06
    érité
    0.06
    اÙĦÛĮ
    0.06
    Activations Density 0.021%

    No Known Activations