© 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. 9101
    Prev
    Next
    INDEX
    Explanations

    asbestos, amphibole, embolization, sarcoidosis

    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
    àºĩ
    -0.07
    ogg
    -0.07
    æĥĬéŃĤ
    -0.07
    umont
    -0.07
    à¸ĺร
    -0.07
    วà¹Į
    -0.07
    ×ŀ×Ļ
    -0.07
     Lecce
    -0.07
    tsx
    -0.07
    erable
    -0.07
    POSITIVE LOGITS
    ä¸ĭæ²ī
    0.07
    aha
    0.07
    æīĵ人
    0.07
    åıįèĢĮä¼ļ
    0.06
    å®¶åľ¨
    0.06
    èĢĮæĺ¯åĽłä¸º
    0.06
     Gem
    0.06
    fee
    0.06
    chio
    0.06
    è¿Ļ个æĸ¹æ³ķ
    0.06
    Activations Density 0.171%

    No Known Activations