© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30487
    Prev
    Next
    INDEX
    Explanations

    programming loops and assignments

    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
     shut
    -0.07
    ylvania
    -0.07
    isman
    -0.07
    .localized
    -0.06
    edale
    -0.06
    è¨Ģä¹ĭ
    -0.06
    åĪĨæŀIJä¸Ģä¸ĭ
    -0.06
    apis
    -0.06
    家åĸ»
    -0.06
     Hal
    -0.06
    POSITIVE LOGITS
    管çIJĨæīĢ
    0.09
    请è¾ĵåħ¥
    0.08
    Į¨
    0.08
    æĪĸ缺
    0.08
    íĶ¼
    0.08
    etra
    0.07
    resolve
    0.07
    reads
    0.07
    uken
    0.07
    uret
    0.07
    Activations Density 0.016%

    No Known Activations