© 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. 31769
    Prev
    Next
    INDEX
    Explanations

    following procedures or process

    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
    serter
    -0.08
    vem
    -0.08
    /ion
    -0.08
     poku
    -0.07
    stelling
    -0.07
    entina
    -0.07
    Ïģιά
    -0.07
    اÛĮد
    -0.07
    strap
    -0.07
    оÑģÑĤоÑı
    -0.07
    POSITIVE LOGITS
     procedural
    0.10
    è¿ĩç¨ĭ
    0.10
     procedures
    0.10
    æµģç¨ĭ
    0.09
     ìłĪì°¨
    0.09
    è¿ĩç¨ĭçļĦ
    0.09
    è¦ģ件
    0.09
     procedure
    0.09
     ìłĪ차를
    0.09
     пÑĢоÑĨедÑĥÑĢ
    0.08
    Activations Density 0.004%

    No Known Activations