© 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. 33150
    Prev
    Next
    INDEX
    Explanations

    solvent compounds and liquids

    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
    ç½®ä¹ĭ
    -0.08
     ÙģÙĤر
    -0.08
    æĬķå°Ħ
    -0.08
    åıªç®¡
    -0.07
     ëıĮ
    -0.07
    累累
    -0.07
    磨ç»ĥ
    -0.07
    康åģ¥
    -0.07
    nud
    -0.07
    çĹĽå¿ĥ
    -0.07
    POSITIVE LOGITS
    溶åīĤ
    0.13
     solvent
    0.12
     liquids
    0.10
    æ··åIJĪ
    0.10
    液
    0.09
    æĮ¥åıij
    0.09
     liquid
    0.09
     blend
    0.09
     mixture
    0.09
    ä¸Ģæ»´
    0.09
    Activations Density 0.082%

    No Known Activations