© 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. 21143
    Prev
    Next
    INDEX
    Explanations

    voltage or current

    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
    dbo
    -0.07
     reg
    -0.07
    é£İåIJ¹
    -0.06
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.06
    ;break
    -0.06
    è¿İéĿ¢
    -0.06
    æľĪèĩ³ä»Ĭ
    -0.06
    à¸Ľà¸£à¸°à¸Ĭ
    -0.06
     kanssa
    -0.06
    edd
    -0.06
    POSITIVE LOGITS
    ãĢģ
    0.15
     maupun
    0.14
     ãĢģ
    0.12
    ä¹Łå¥½
    0.12
    ãĢģãĢģ
    0.11
    ãģĦãģŁãĤĬ
    0.11
    æĢ§åĴĮ
    0.10
    æĿĥåĴĮ
    0.10
    à¹ģละ
    0.10
    æķ°åĴĮ
    0.10
    Activations Density 0.588%

    No Known Activations