© 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. 26783
    Prev
    Next
    INDEX
    Explanations

    asking "what"

    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
     опÑĢав
    -0.08
    æľīåħ³äºĭ项
    -0.08
    oose
    -0.08
    itra
    -0.08
    å®ŀåIJį
    -0.08
    yor
    -0.07
    ĽĦ
    -0.07
    éĿĴåħī
    -0.07
    hausen
    -0.07
    Down
    -0.07
    POSITIVE LOGITS
    nict
    0.08
    åĨ³å®ļçĿĢ
    0.08
    æĪĸ缺
    0.07
    æĶ¯éħį
    0.07
    éĴ¥
    0.06
    èįļ
    0.06
    ç£
    0.06
    _binding
    0.06
    å±ķ
    0.06
    ãģ¦ãĤĭ
    0.06
    Activations Density 0.001%

    No Known Activations