© 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. 23785
    Prev
    Next
    INDEX
    Explanations

    actions, Contribution, way to, men

    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
    ouser
    -0.08
    ADER
    -0.07
    éĽĦé¹°
    -0.07
    øy
    -0.07
    å¤ļåħĥåĮĸçļĦ
    -0.07
    izr
    -0.06
    zend
    -0.06
    å¦ĸå¨Ĩ
    -0.06
     Syntax
    -0.06
    NotFoundError
    -0.06
    POSITIVE LOGITS
    å¤ĦçIJĨæĸ¹å¼ı
    0.08
    æīĵ交éģĵ
    0.08
    guid
    0.08
    åħ³æ³¨
    0.08
    çIJĨ解åĴĮ
    0.07
    è¯Ħä¼°
    0.07
    omatic
    0.07
     Bench
    0.07
    æĮĩ导
    0.07
     evaluation
    0.07
    Activations Density 0.495%

    No Known Activations