© 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. 20427
    Prev
    Next
    INDEX
    Explanations

    example sentences

    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
    1
    -0.06
    ere
    -0.06
    p
    -0.06
    t
    -0.06
    æµ·æ¹¾
    -0.06
    æľ¬ç§ij
    -0.06
    2
    -0.05
    ↵
    -0.05
     Biro
    -0.05
    åľ¨ä¸Ģ
    -0.05
    POSITIVE LOGITS
    å®ī好
    0.09
    gnore
    0.08
    ç»´æĬ¤åĴĮ
    0.08
    俱ä¹IJéĥ¨
    0.08
    ç¿°
    0.08
    KY
    0.08
    |string
    0.08
    ä¸Ģæĸ°çļĦ
    0.08
     *[
    0.08
    大åĪ©
    0.08
    Activations Density 0.020%

    No Known Activations