© 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. 50996
    Prev
    Next
    INDEX
    Explanations

    simile comparisons

    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
    å¦ĤåĪĿ
    -0.08
    _DF
    -0.08
    ertet
    -0.08
    çĴĢ
    -0.08
    人éģĵ
    -0.08
    缸å½ĵäºİ
    -0.07
    æĶ¶èĹıæľ¬ç«Ļ
    -0.07
    åIJĥèĤī
    -0.07
    æīįæĺ¯çľŁæŃ£çļĦ
    -0.07
    çļĦ人åĴĮ
    -0.07
    POSITIVE LOGITS
    ä¸Ģæł·
    0.10
    ä¸Ģ樣
    0.09
    åĸ»
    0.09
     váºŃy
    0.08
    éĤ£æł·
    0.08
    æ¯Ķåĸ»
    0.08
    éĤ£èĪ¬
    0.08
     analogy
    0.08
    à¸īะà¸Ļัà¹īà¸Ļ
    0.07
    åıĪå¦Ĥ
    0.07
    Activations Density 0.042%

    No Known Activations