© 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. 56021
    Prev
    Next
    INDEX
    Explanations

    precondition or breaks in activity

    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
    ãģ¯ãĤĤãģ¡ãĤįãĤĵ
    -0.07
    è¿Ļä¸ĭ
    -0.07
    iterated
    -0.07
    å½ĵä¹ĭæĹłæĦ§
    -0.07
    astle
    -0.06
    深深
    -0.06
    consistent
    -0.06
    _NB
    -0.06
    éģ©çĶ¨æĸ¼
    -0.06
    éļ¾æĢª
    -0.06
    POSITIVE LOGITS
    è½¬æľº
    0.13
    好æ¶Īæģ¯
    0.12
     mitig
    0.11
    æĮ½åĽŀ
    0.11
     hopeful
    0.11
    è¡¥æķij
    0.10
    è¿ĺ好
    0.10
     thankfully
    0.10
    幸
    0.10
    æķij
    0.10
    Activations Density 0.486%

    No Known Activations