© 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. 1263
    Prev
    Next
    INDEX
    Explanations

    "option" status, "template" in, "motto" is, "square" in, "card" in, "keeps" looping, "error" in, "What" is

    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
     ‘
    -0.08
    culares
    -0.08
    ContentSize
    -0.08
    æīĢè°ĵ
    -0.08
    logg
    -0.08
     intit
    -0.07
    æīĢè°ĵçļĦ
    -0.07
    à¥į
    -0.07
     âĢļ
    -0.07
    éķ¿æĮīäºĮç»´çłģ
    -0.07
    POSITIVE LOGITS
    ä¼ĹæīĢåij¨çŁ¥
    0.12
    åĭĩå¾Ģ缴åīį
    0.11
    ãĢģ“
    0.10
    缸è¾ħ缸æĪIJ
    0.09
    æĸ°åĬłåĿ¡
    0.09
    åĬłæĭ¿å¤§
    0.08
    顾åIJįæĢĿä¹ī
    0.07
    åŃĹæł·
    0.07
     referring
    0.07
    æĮĩçļĦæĺ¯
    0.06
    Activations Density 0.259%

    No Known Activations