© 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. 62018
    Prev
    Next
    INDEX
    Explanations

    ordinal number + noun

    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
    éĢĿ
    -0.08
    ä¸Ģå¤ķ
    -0.08
    uite
    -0.08
    ATAN
    -0.08
    mars
    -0.08
    æĸĩæijĺ
    -0.07
    anze
    -0.07
     sih
    -0.07
    ç³
    -0.07
    åĪ«æĹł
    -0.07
    POSITIVE LOGITS
     ë²Ī째
    0.09
    åĴĮ第
    0.09
    åĴĮ第äºĮ
    0.08
     kalinya
    0.08
     onward
    0.08
     ÙĪاÙĦØ«
    0.08
    ç¬¬åĽĽä¸ª
    0.07
    第ä¸ĥ
    0.07
    æŀĿèĬ±
    0.07
     onwards
    0.07
    Activations Density 0.099%

    No Known Activations