© 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. 34288
    Prev
    Next
    INDEX
    Explanations

    lecture about America

    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
    ardi
    -0.07
    çļĵ
    -0.07
    folio
    -0.07
    çĥĺ
    -0.07
    èĩªåıij
    -0.07
    ikko
    -0.06
    ProcessEvent
    -0.06
    æ²»
    -0.06
    çĨĻ
    -0.06
    飬
    -0.06
    POSITIVE LOGITS
    ains
    0.07
     ::
    0.07
    enj
    0.07
    ساÙĨÛĮ
    0.07
    æij©ç¾¯
    0.07
    寮
    0.07
    è¦ģçŁ¥éģĵ
    0.06
    ugg
    0.06
     pseud
    0.06
    å®ŀå®ŀåľ¨
    0.06
    Activations Density 0.004%

    No Known Activations