© 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. 51886
    Prev
    Next
    INDEX
    Explanations

    reaction hydrogenation catalysts

    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
    æĹ©çĿ¡
    -0.07
    竺
    -0.06
    ç»´æĬ¤åĴĮ
    -0.06
    åĭ¤
    -0.06
    åīĶéĻ¤
    -0.06
    0
    -0.06
    w
    -0.06
    å®ŀéĻħéľĢè¦ģ
    -0.05
    imp
    -0.05
    orial
    -0.05
    POSITIVE LOGITS
    çļĦåıįåºĶ
    0.10
    å®īåħ¨è¯ĦåĪĨ
    0.08
    éĶ¦æłĩ
    0.08
    åıįåºĶ
    0.08
     reactions
    0.08
    bung
    0.08
     react
    0.08
    jol
    0.08
    ç«ŀ
    0.08
    odia
    0.08
    Activations Density 0.019%

    No Known Activations