© 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. 29514
    Prev
    Next
    INDEX
    Explanations

    syndrome, inflammation, idiopathic, manifestations

    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°ĶèĴĻ
    -0.08
    ษ
    -0.08
    æ¥
    -0.08
    ffer
    -0.08
    ubs
    -0.07
    çĨŁç»ĥ
    -0.07
    èį·
    -0.07
     UNUSED
    -0.07
    çijľ
    -0.07
    unny
    -0.07
    POSITIVE LOGITS
    ç½ķè§ģ
    0.09
    ç½ķè§ģçļĦ
    0.09
    åıijçĶŁåľ¨
    0.09
    åıijçĶŁäºİ
    0.09
     unusual
    0.09
    å¤ļè§ģäºİ
    0.08
     manifestations
    0.08
     rare
    0.08
    rare
    0.08
    åģĩ
    0.08
    Activations Density 1.304%

    No Known Activations