© 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. 63603
    Prev
    Next
    INDEX
    Explanations

    "how" questions or "whether" statements

    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
    kul
    -0.06
    èĩªçĦ¶
    -0.06
    ona
    -0.06
    çļĦèĩªçĦ¶
    -0.06
    ilot
    -0.06
    sob
    -0.06
    ä¸įå¤ĸ
    -0.06
     Bref
    -0.06
    BC
    -0.06
    çļĦæľĢé«ĺ
    -0.06
    POSITIVE LOGITS
    éĻ¤æѤ
    0.08
    使ä¹ĭ
    0.08
    对åħ¶è¿Ľè¡Į
    0.08
    éĻ¤æѤä¹ĭå¤ĸ
    0.07
    ä¹ĭçªĹ
    0.07
    ارات
    0.07
    /framework
    0.07
    æİĸ
    0.07
    WAYS
    0.07
    为ä¹ĭ
    0.07
    Activations Density 0.202%

    No Known Activations