© 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. 42184
    Prev
    Next
    INDEX
    Explanations

    penalties and jail time

    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
    sker
    -0.08
    plan
    -0.08
    æī¹
    -0.08
    åħ¨æľ¬å°ı说
    -0.07
    çĸij
    -0.07
    uintptr
    -0.07
    å±ķå¼Ģåħ¨æĸĩ
    -0.07
    ç¼ĵåĨ²
    -0.07
    æ¬łç¨İåħ¬åijĬ
    -0.07
     Gors
    -0.07
    POSITIVE LOGITS
     range
    0.08
     ranging
    0.08
     ranges
    0.07
    ubo
    0.07
     depending
    0.07
     вплоÑĤÑĮ
    0.07
    ä¸įæĪIJ
    0.07
     spectrum
    0.07
     ranged
    0.07
    åŁºç¡Ģä¸Ĭ
    0.07
    Activations Density 0.027%

    No Known Activations