© 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. 19865
    Prev
    Next
    INDEX
    Explanations

    the Software

    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
    of
    -0.07
    ep
    -0.07
    iv
    -0.06
    è²Į
    -0.06
     vergeben
    -0.06
    Ãĥ
    -0.06
    cir
    -0.06
    ä¸įä½ıäºĨ
    -0.06
    xx
    -0.06
    èĬ®
    -0.06
    POSITIVE LOGITS
    elai
    0.08
    undler
    0.08
    _docs
    0.08
    åįģæĿ¡
    0.08
    aista
    0.08
    abilidade
    0.07
    èĥ½åģļ
    0.07
    (ai
    0.07
    fbe
    0.07
    etas
    0.07
    Activations Density 0.003%

    No Known Activations