© 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. 11442
    Prev
    Next
    INDEX
    Explanations

    collections, tables, and catalog

    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
    reno
    -0.06
    éħįæĪ´
    -0.06
    thal
    -0.06
    /downloads
    -0.06
    ients
    -0.06
    ilee
    -0.06
    inkel
    -0.06
    arseille
    -0.06
    èĩ³äºİ
    -0.06
    æĸ§
    -0.06
    POSITIVE LOGITS
    appare
    0.08
    aho
    0.08
    datable
    0.08
    áĥIJáĥ®
    0.08
    actable
    0.07
    æŀģ好
    0.07
     agora
    0.07
    asta
    0.07
    ä¹ĭä¸Ģå°±æĺ¯
    0.07
     rectific
    0.07
    Activations Density 0.241%

    No Known Activations