© 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. 2576
    Prev
    Next
    INDEX
    Explanations

    code assignments and function calls

    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
    éĶĢåĶ®åıĬ
    -0.07
    pped
    -0.07
    空
    -0.07
    为åĩĨ
    -0.06
    elon
    -0.06
    为空
    -0.06
    çļĦæĺ¯
    -0.06
    dar
    -0.06
    å¾Ī满æĦı
    -0.06
    enni
    -0.06
    POSITIVE LOGITS
    ObjectContext
    0.08
    -pay
    0.08
     mẽ
    0.08
    aternity
    0.08
     recourse
    0.07
    ãģĹãĤĤ
    0.07
    æīĢèĥ½åıĬ
    0.07
    วà¸ģ
    0.07
    ä¸ĭåIJĮ
    0.07
    zens
    0.07
    Activations Density 0.073%

    No Known Activations