© 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. 19819
    Prev
    Next
    INDEX
    Explanations

    by-products, wastes, generated materials

    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
    ÙĦÙĬÙĩ
    -0.07
    缮çļĦ
    -0.07
    æįī
    -0.07
    综åIJĪæĶ¹éĿ©
    -0.07
    ogna
    -0.06
    ãģ«åħ¥
    -0.06
    缮çļĦçļĦ
    -0.06
    çŀ°
    -0.06
    éĿĴåħī
    -0.06
    ëł
    -0.06
    POSITIVE LOGITS
    çļĦ产çĶŁ
    0.10
    åī¯äº§åĵģ
    0.09
    æĢİä¹Īå¤ĦçIJĨ
    0.08
     اÙĦÙĨات
    0.08
     GENERATED
    0.08
    à¸Īาà¸ģà¸ģาร
    0.08
    产åĩº
    0.08
     generated
    0.08
    æĶ¶éĽĨçļĦ
    0.08
    çļĦå¤ĦçIJĨ
    0.08
    Activations Density 0.091%

    No Known Activations