© 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. 20217
    Prev
    Next
    INDEX
    Explanations

    medication dosage forms

    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
     uÄŁ
    -0.09
    çĿĢçī©
    -0.09
    æľĢæĸ°è¯Ħ论
    -0.09
    aner
    -0.09
    etal
    -0.08
    åѦæĬ¥
    -0.08
    egn
    -0.08
    æ©Ħæ¦Ħæ²¹
    -0.08
    å±ķå¼Ģåħ¨æĸĩ
    -0.08
     nurt
    -0.08
    POSITIVE LOGITS
    åĴĢ
    0.08
     chew
    0.08
    ä¸Ģç²Ĵ
    0.07
    åį°æľī
    0.07
    åĪ¶æĪIJ
    0.07
     tablets
    0.06
    ç²Ĵ
    0.06
    ä¸Ģé¢Ĺ
    0.06
    åIJ«æľī
    0.06
    åīĤ
    0.06
    Activations Density 0.069%

    No Known Activations