© 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. 41848
    Prev
    Next
    INDEX
    Explanations

    mathematical notation indices

    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
    ãģĴ
    -0.07
    äg
    -0.06
    awa
    -0.06
    ÑĪÑĭ
    -0.06
    åIJįåī¯åħ¶å®ŀçļĦ
    -0.06
    åıįæŃ£
    -0.06
    对åºĶçļĦ
    -0.06
    ä¼¼
    -0.06
    èĤ¢
    -0.06
     wrap
    -0.06
    POSITIVE LOGITS
    ä»»æĦı
    0.13
    ä¸ŃçļĦä»»æĦı
    0.12
    æŁIJ
    0.11
    ä»»ä½ķ
    0.11
    çļĦä»»ä½ķ
    0.11
     cualquier
    0.11
    ä»»ä¸Ģ
    0.11
     лÑİбого
    0.11
    以任ä½ķ
    0.11
     any
    0.10
    Activations Density 0.120%

    No Known Activations