© 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. 20779
    Prev
    Next
    INDEX
    Explanations

    right-handed

    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
    iato
    -0.08
    ogna
    -0.07
    ISA
    -0.07
    ήμε
    -0.07
    ÅĪa
    -0.07
    verage
    -0.07
    å¼ı为
    -0.07
    ÑĢаÑĤи
    -0.07
    謹
    -0.07
    acus
    -0.07
    POSITIVE LOGITS
    åIJĦèĩªçļĦ
    0.21
    åIJĦèĩª
    0.21
     respectively
    0.16
    ãģĿãĤĮãģŀãĤĮ
    0.15
    åIJĦæľī
    0.14
     respective
    0.14
    åĪĨåĪ«æĺ¯
    0.13
    åĪĨåĪ«ä¸º
    0.13
    åĪĨåĪ«
    0.12
    ãģļãģ¤
    0.12
    Activations Density 0.155%

    No Known Activations