© 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. 26711
    Prev
    Next
    INDEX
    Explanations

    number sequences or code

    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
    urin
    -0.08
    帯
    -0.08
    udara
    -0.07
    elius
    -0.07
    çĪ¶
    -0.07
    خش
    -0.07
    ç»Ļ大家æݨèįIJ
    -0.07
    娱
    -0.07
    /pub
    -0.07
    عÙĦ
    -0.06
    POSITIVE LOGITS
    tram
    0.07
    hack
    0.07
    ä¸įçĿĢ
    0.06
    æĭ¾
    0.06
    age
    0.06
    lage
    0.06
    ÑĢиÑģÑĤи
    0.06
    lever
    0.06
    odle
    0.06
    nger
    0.06
    Activations Density 0.018%

    No Known Activations