© 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. 13155
    Prev
    Next
    INDEX
    Explanations

    state, progress, rates

    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
    reen
    -0.07
    _formats
    -0.07
    éĩijé¦Ļ
    -0.07
     fondo
    -0.07
    fer
    -0.07
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    ire
    -0.07
    æł·æł·
    -0.07
    çīĩçīĩ
    -0.06
    .gb
    -0.06
    POSITIVE LOGITS
    ønd
    0.07
     pretty
    0.07
    iki
    0.06
    /embed
    0.06
    _ctl
    0.06
    urgi
    0.06
    veli
    0.06
    akis
    0.06
    è¾ĥ大
    0.06
    çİīé¾Ļ
    0.06
    Activations Density 0.013%

    No Known Activations