© 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. 29468
    Prev
    Next
    INDEX
    Explanations

    decoction

    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
    è¶ħä¹İ
    -0.08
    奥å°Ķ
    -0.08
    å·ŀç«ĭ
    -0.08
    çĮľ
    -0.08
    é³į
    -0.08
    个人页
    -0.07
    çĶŁæ´»ä¼ļ
    -0.07
    weiler
    -0.07
    è¿Ļç§įçĸ¾çĹħ
    -0.07
    éľĵ
    -0.07
    POSITIVE LOGITS
    åĪ¶æĪIJçļĦ
    0.08
    ä¸Ńèį¯
    0.07
    اÙħØ©
    0.07
    åĩĮäºij
    0.07
    åĺ±
    0.07
    åĪ¶æĪIJ
    0.07
    èĮľ
    0.07
     deco
    0.07
    æĮīè§Ħå®ļ
    0.06
     оÑĤваÑĢ
    0.06
    Activations Density 0.006%

    No Known Activations