© 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. 40130
    Prev
    Next
    INDEX
    Explanations

    Linux, sudo, rails, redirect

    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
    etto
    -0.07
    cano
    -0.07
    QUIRE
    -0.07
    quire
    -0.07
    kena
    -0.06
     Telekom
    -0.06
    itch
    -0.06
    uba
    -0.06
    udz
    -0.06
    aczy
    -0.06
    POSITIVE LOGITS
    éĢģèĩ³
    0.06
    _LAYOUT
    0.06
    驻马
    0.06
    ilies
    0.06
    ä½Ĩä¸įéĻIJäºİ
    0.06
    âĢij
    0.06
    Ø¡
    0.06
    istir
    0.06
    æĪĪ
    0.06
    欧åħĥåĮº
    0.06
    Activations Density 0.067%

    No Known Activations