© 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. 25244
    Prev
    Next
    INDEX
    Explanations

    process stages

    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
    çķĻå¿ĥ
    -0.08
    æİĮæı¡å¥½
    -0.08
    类似çļĦ
    -0.07
    nts
    -0.07
    OutOf
    -0.07
    åĩºæģ¯
    -0.07
     Kul
    -0.07
    íĭ°ë¸Į
    -0.07
    æĹĹé¼ĵ
    -0.07
    ashed
    -0.07
    POSITIVE LOGITS
    -ready
    0.09
    Ready
    0.09
     ready
    0.09
    ready
    0.09
     Ready
    0.09
    ä¸ºçĽ®çļĦ
    0.08
     later
    0.08
     readiness
    0.08
    ãģĿãģ®ãģ¾ãģ¾
    0.08
    hev
    0.07
    Activations Density 0.318%

    No Known Activations