© 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. 33218
    Prev
    Next
    INDEX
    Explanations

    units of measurement and quantities

    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
     inilah
    -0.09
     itulah
    -0.08
     infatti
    -0.08
     certes
    -0.07
    ä¹Łç¡®å®ŀ
    -0.07
     bowiem
    -0.07
    FromString
    -0.07
    ÑĨÑĮ
    -0.07
    olgen
    -0.07
    ãĤĵãģ©
    -0.07
    POSITIVE LOGITS
     versus
    0.10
    好åij¢
    0.09
     ÙĪÙĥÙĬÙģ
    0.09
    以åıĬå¦Ĥä½ķ
    0.09
    ä½łåij¢
    0.08
    åij¢
    0.08
    çļĦåij¢
    0.08
    以åıĬåľ¨
    0.08
    )?.
    0.08
     ?>>
    0.08
    Activations Density 0.390%

    No Known Activations