© 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. 46384
    Prev
    Next
    INDEX
    Explanations

    data structure representations

    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
    GetType
    -0.09
    BuilderFactory
    -0.08
    verband
    -0.08
    è¨Ģä¹ĭ
    -0.08
    াহ
    -0.08
    osting
    -0.08
    apolis
    -0.08
    ooks
    -0.08
    etheless
    -0.08
    umbing
    -0.08
    POSITIVE LOGITS
     representing
    0.12
    çĶ¨ä»¥
    0.10
    represent
    0.09
    代表
    0.09
    çĶ¨æĿ¥
    0.09
    ä¸Ń表示
    0.09
    代表äºĨ
    0.08
     represents
    0.08
    çĶ¨äºİ
    0.08
    æĹ¶è¡¨ç¤º
    0.07
    Activations Density 0.063%

    No Known Activations