© 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. 17991
    Prev
    Next
    INDEX
    Explanations

    maximum or maximal values

    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
    witz
    -0.08
    asca
    -0.07
     changing
    -0.06
    çħ§çĿĢ
    -0.06
     inappropriate
    -0.06
    cis
    -0.06
    ino
    -0.06
    asc
    -0.06
     Changing
    -0.06
    æĮīè¦ģæ±Ĥ
    -0.06
    POSITIVE LOGITS
    æľĢ大åĮĸ
    0.15
     maxim
    0.14
     maximize
    0.13
    æľĢå¤ļ
    0.12
    -max
    0.12
     макÑģ
    0.12
     Maxim
    0.12
     maximal
    0.12
     maximizing
    0.12
     макÑģималÑĮ
    0.12
    Activations Density 0.025%

    No Known Activations