© 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. 16397
    Prev
    Next
    INDEX
    Explanations

    FETCH NEXT FROM

    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
    chure
    -0.07
    ä¸ĢåĬ¨
    -0.07
    ilation
    -0.07
    娲
    -0.07
    çªģçĦ¶åıijçİ°
    -0.07
    гоÑĢа
    -0.07
    çİĭ大
    -0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
    дзе
    -0.07
    ä¸ĭ载次æķ°
    -0.07
    POSITIVE LOGITS
    è¤Ĵ
    0.07
    é²
    0.06
    ue
    0.06
    ulet
    0.06
    asm
    0.06
    iban
    0.06
    upon
    0.06
    unic
    0.06
     duly
    0.06
    ано
    0.06
    Activations Density 0.144%

    No Known Activations