© 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. 12616
    Prev
    Next
    INDEX
    Explanations

    industry experts

    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
    este
    -0.07
    abei
    -0.07
    å§ĭ
    -0.06
    å®£ä¼łåįķ
    -0.06
    izard
    -0.06
    ãģĭãĤı
    -0.06
    iscard
    -0.06
    idget
    -0.06
    ãĥ»
    -0.06
    åıĤ天
    -0.06
    POSITIVE LOGITS
    人ä¸Ģ
    0.08
    à¹īว
    0.08
    è¿Ļç§įåģļæ³ķ
    0.08
    amines
    0.08
    มà¹Į
    0.07
    AMY
    0.07
    幸è¿IJçļĦæĺ¯
    0.07
    缸åħ³æݨèįIJ
    0.07
    åĴĮä¸į足
    0.07
    çļĦæľĭåıĭåı¯ä»¥
    0.07
    Activations Density 0.008%

    No Known Activations