© 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. 25355
    Prev
    Next
    INDEX
    Explanations

    thyroid abnormalities

    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
    åĮķ
    -0.07
     rigged
    -0.07
     suprem
    -0.07
    å¸ĥæĸ¯
    -0.06
    åģļ人çļĦ
    -0.06
     unanim
    -0.06
    éľĩæĴ¼
    -0.06
    пл
    -0.06
     disemb
    -0.06
     extraordinarily
    -0.06
    POSITIVE LOGITS
    äºĽè®¸
    0.09
    å°ij许
    0.09
    éļIJéļIJ
    0.09
     nieco
    0.08
    äºĨä¸Ģä¸Ŀ
    0.08
    微微
    0.08
     slightly
    0.08
    -lite
    0.08
    hints
    0.08
    æĺ¾å¾ĹæľīäºĽ
    0.08
    Activations Density 0.034%

    No Known Activations