© 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. 49257
    Prev
    Next
    INDEX
    Explanations

    Eigen code

    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
    åıĬæł¼
    -0.08
    orsch
    -0.07
    åıįæŃ£
    -0.07
    aurus
    -0.07
    auce
    -0.07
    ä¸ĢåºĶ
    -0.07
    åĽłä¸ºè¿ĻäºĽ
    -0.07
    aufs
    -0.06
    emps
    -0.06
    доÑĢа
    -0.06
    POSITIVE LOGITS
    ä¸ĭåĪĹåħ³äºİ
    0.10
    ä¸ĭåĪĹ
    0.09
    ä¸ĭåĪĹ说æ³ķ
    0.09
    æľĢéĢĤåIJĪ
    0.07
    æľīä¸ĭåĪĹ
    0.07
    å¦Ĥæŀľä¸Ģ个
    0.07
    ä¸ĭéĿ¢æĺ¯
    0.07
    被èªī为
    0.07
    _ARG
    0.07
    ä¸ĭéĿ¢çļĦ
    0.07
    Activations Density 0.035%

    No Known Activations