© 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. 8749
    Prev
    Next
    INDEX
    Explanations

    package management dependencies

    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
    深交æīĢ
    -0.08
    毡
    -0.08
    éļĭ
    -0.07
    bert
    -0.07
    seau
    -0.07
    设计éĻ¢
    -0.07
    æ·±åľ³è¯ģåĪ¸äº¤æĺĵæīĢ
    -0.07
    æĮª
    -0.06
    秣åĶ®
    -0.06
    umni
    -0.06
    POSITIVE LOGITS
    .debian
    0.09
     xen
    0.07
     packaging
    0.07
     systemd
    0.07
     watchdog
    0.07
    .defer
    0.07
    edos
    0.07
    PKG
    0.07
    /pkg
    0.07
     reboot
    0.07
    Activations Density 0.099%

    No Known Activations