© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50328
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    ahu
    -0.07
     Ritter
    -0.06
    IZA
    -0.06
    å¾Ģå¾Ģ
    -0.06
    对ä»ĺ
    -0.06
     nomin
    -0.06
    槻
    -0.06
     Grav
    -0.06
    ikut
    -0.05
    粧
    -0.05
    POSITIVE LOGITS
    kannya
    0.09
     Decompiled
    0.08
    æĿ¡
    0.07
    \/
    0.07
    holm
    0.07
    nist
    0.07
    رÙĬÙħ
    0.07
    /]
    0.07
    çĶŁæķĪä¹ĭæĹ¥èµ·
    0.07
     noqa
    0.07
    Activations Density 1.056%

    No Known Activations