© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7280
    Prev
    Next
    INDEX
    Explanations

    oropharyngeal path

    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
    mailto
    -0.07
    .trailing
    -0.06
    allet
    -0.06
    ensp
    -0.06
    éķ°
    -0.06
    æľĢçĪ±çļĦ
    -0.06
    æĪijçļĦä¸ĸçķĮ
    -0.06
    æĤ£äºĨ
    -0.06
    lbrace
    -0.06
    INES
    -0.06
    POSITIVE LOGITS
    èµ·çłģ
    0.08
    zte
    0.08
    âĢ¦âĢ¦
    0.07
    åĩºåIJį
    0.07
    		  ↵
    0.07
    \_
    0.07
    ä¸įæ¸ħæ¥ļ
    0.07
    æij
    0.07
    zman
    0.07
    âĢ¦âĢ¦âĢ¦âĢ¦
    0.07
    Activations Density 0.022%

    No Known Activations