© 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. 16394
    Prev
    Next
    INDEX
    Explanations

    assertions, medical details, and non-English words

    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
    ho
    -0.08
    åıªæĺ¯ä¸Ģç§į
    -0.07
    çµ
    -0.06
    æŨ
    -0.06
    ires
    -0.06
    _REQUIRE
    -0.06
    acea
    -0.06
    é¦ĸåħĪ
    -0.06
    onia
    -0.06
    并就
    -0.06
    POSITIVE LOGITS
     zatem
    0.08
    æį¢è¨Ģä¹ĭ
    0.08
     Yani
    0.08
     Impro
    0.07
    -interest
    0.07
    ä¹Łå°±æĺ¯è¯´
    0.07
    ä¹Łå°±æĺ¯èªª
    0.07
    ilden
    0.07
    åij½åIJį为
    0.07
     Jadi
    0.07
    Activations Density 0.011%

    No Known Activations