© 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. 9649
    Prev
    Next
    INDEX
    Explanations

    cells, tissues, systems, Force

    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
    urm
    -0.08
    azo
    -0.08
    OCK
    -0.08
    æīĢåľ¨åįķä½į
    -0.08
    çĦ¶å¤§
    -0.08
    :this
    -0.07
    insula
    -0.07
    丢
    -0.07
     запи
    -0.07
     pilota
    -0.07
    POSITIVE LOGITS
    ä¸ŃçļĦä¸Ģç§į
    0.07
    ä¸ŃæĮĩ
    0.07
    缮çļĦæĺ¯ä¸ºäºĨ
    0.07
     à¹ģละà¹Ģà¸Ľà¹ĩà¸Ļ
    0.07
    çĶ¨æĿ¥
    0.07
    çļĦä¸Ģç§į
    0.07
    ä¸Ń被
    0.06
    主è¦ģçĶ¨äºİ
    0.06
    å®ĥæĺ¯ä¸Ģç§į
    0.06
    èĢĮå¾ĹåIJį
    0.06
    Activations Density 0.375%

    No Known Activations