© 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. 9216
    Prev
    Next
    INDEX
    Explanations

    parts of a building or structure

    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
    èħ¾
    -0.07
    .misc
    -0.06
    æģŃ
    -0.06
    ionato
    -0.06
    åıĤ
    -0.06
     involve
    -0.06
    vangen
    -0.06
     Avis
    -0.06
    ä¸įå¿ĺ
    -0.06
    å°±æĺ¯æĪij们çļĦ
    -0.06
    POSITIVE LOGITS
    è¿Ļç§įä¸ľè¥¿
    0.12
    çļĦåŃĺåľ¨
    0.11
    踪影
    0.10
    less
    0.10
    åıĸèĢĮ代ä¹ĭ
    0.10
    代ãĤıãĤĬãģ«
    0.10
    踪迹
    0.09
    è¿Ļä¸ªä¸ľè¥¿
    0.09
    losigkeit
    0.09
    -less
    0.08
    Activations Density 0.093%

    No Known Activations