© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22794
    Prev
    Next
    INDEX
    Explanations

    education and media topics

    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
    ieber
    -0.09
    åĽ½å¼º
    -0.08
    allet
    -0.08
    ÅĤod
    -0.07
    幸
    -0.07
    LEC
    -0.07
    大ä¸ĸçķĮ
    -0.07
    åł¡
    -0.07
    ä¸İæĮijæĪĺ
    -0.07
    /&
    -0.06
    POSITIVE LOGITS
    å®ļä¹ī为
    0.09
    æ³ķæĺ¯
    0.08
     defined
    0.08
     definition
    0.08
    æĢ§æĺ¯
    0.07
    çļĦå®ļä¹ī
    0.07
    ä¿¡æģ¯çĶ±
    0.07
    Definition
    0.07
    ç¿ł
    0.06
    помним
    0.06
    Activations Density 0.075%

    No Known Activations