© 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. 19513
    Prev
    Next
    INDEX
    Explanations

    "given" followed by a structure description

    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
    jenigen
    -0.09
    带ä¸Ĭ
    -0.07
    ä¹ĭæīĢ以
    -0.07
     if
    -0.07
    iped
    -0.06
    arken
    -0.06
    表çİ°åĩºæĿ¥
    -0.06
    åĨħ容åĮħæĭ¬
    -0.06
     matters
    -0.06
    ).__
    -0.06
    POSITIVE LOGITS
    ,it
    0.10
    并已
    0.10
     ",",
    0.09
    人æĿ¥è¯´
    0.08
    è¿Ļä¹Īä¸Ģ个
    0.08
    åį´ä¸įçŁ¥éģĵ
    0.08
    ,is
    0.08
    çļĦ人æĿ¥è¯´
    0.08
     maka
    0.08
     sẵn
    0.08
    Activations Density 0.063%

    No Known Activations