© 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. 17452
    Prev
    Next
    INDEX
    Explanations

    medical dysfunction and disorders

    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
    å°Ĭéĩį
    -0.07
    æ¯ķç«Ł
    -0.06
    ani
    -0.06
    ä¸įå¿ĺ
    -0.06
    ãĥĽãĥ«
    -0.06
    lian
    -0.06
    rea
    -0.06
    åĨµä¸Ķ
    -0.05
    æĹ¢çĦ¶
    -0.05
    ä¹ħè¿Ŀ
    -0.05
    POSITIVE LOGITS
    æĺ¯å¯¼èĩ´
    0.15
    导èĩ´äºĨ
    0.13
     inilah
    0.12
    æĺ¯æݨåĬ¨
    0.11
    åĨ³å®ļçĿĢ
    0.10
    èĢĮ导èĩ´
    0.10
    æĺ¯åħ³éĶ®
    0.10
    ä»İèĢĮ导èĩ´
    0.10
     leads
    0.10
    æľīèĩ´
    0.10
    Activations Density 0.330%

    No Known Activations