© 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. 24338
    Prev
    Next
    INDEX
    Explanations

    technical terms in code

    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
     (
    -0.06
    ,
    -0.06
    -0.06
     kir
    -0.06
    ÙĪÙĬÙĩ
    -0.05
    çķĶ
    -0.05
    obia
    -0.05
     cross
    -0.05
    .RESULT
    -0.05
    ಷà³įà²Ł
    -0.05
    POSITIVE LOGITS
    agak
    0.09
    æĸ¹éĿ¢çļĦçŁ¥è¯Ĩ
    0.09
    大人们
    0.08
    端起
    0.08
     "~/
    0.08
    ÑĢге
    0.08
    istol
    0.08
    ogg
    0.08
    ÛķÚ©
    0.07
    itty
    0.07
    Activations Density 0.073%

    No Known Activations