© 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. 63189
    Prev
    Next
    INDEX
    Explanations

    extracting solvents like ethyl acetate

    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
    rou
    -0.07
     uniform
    -0.07
    å¤įå·¥
    -0.06
    ument
    -0.06
    åľ¨å¤ĸ
    -0.06
    kel
    -0.06
    éŀŃ
    -0.06
    omon
    -0.06
    家æĶ¿
    -0.06
    elt
    -0.06
    POSITIVE LOGITS
    æıIJåıĸçī©
    0.08
    çĪ±ä¸½ä¸Ŀ
    0.08
     tây
    0.08
    ewire
    0.08
    rawl
    0.08
    icole
    0.08
    ÅĤaw
    0.08
    ÑĦелÑĮ
    0.08
    icot
    0.08
    ä¸ĥä¸Ģ
    0.07
    Activations Density 0.011%

    No Known Activations