© 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. 21738
    Prev
    Next
    INDEX
    Explanations

    unchanged levels

    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
    mgr
    -0.07
    ohen
    -0.07
    漫天
    -0.07
    enster
    -0.07
    å°ģ顶
    -0.07
    ä¸įèĥľ
    -0.07
    ç¼Ī
    -0.07
    lix
    -0.06
    æĤ²æĥ¨
    -0.06
    akh
    -0.06
    POSITIVE LOGITS
     unchanged
    0.12
     slight
    0.11
    æĹłæģĻ
    0.10
     normal
    0.10
     unaffected
    0.10
    æĺ¯æŃ£å¸¸çļĦ
    0.10
    æĹłå¼Ĥ
    0.10
     subtly
    0.10
    æŃ£å¸¸çļĦ
    0.10
    çķ¥å¾®
    0.10
    Activations Density 0.346%

    No Known Activations