© 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. 27837
    Prev
    Next
    INDEX
    Explanations

    low conditions

    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
    ìĤ°ì§Ģ
    -0.08
    ience
    -0.07
    -lite
    -0.07
    ä¹Łä¸įåĨį
    -0.07
    DataStream
    -0.07
    山河
    -0.07
    ä¸įéĹ´æĸŃ
    -0.07
    å±ĬæŶ
    -0.06
    ä¸įåĨįæĺ¯
    -0.06
     désormais
    -0.06
    POSITIVE LOGITS
     (<
    0.13
     (\<
    0.10
    åĪ°ä¸Ń
    0.10
    åĴĮä¸Ń
    0.10
    (<
    0.09
    /small
    0.09
    å°ļ
    0.08
    å°ļåľ¨
    0.08
    uros
    0.08
     [<
    0.07
    Activations Density 0.068%

    No Known Activations