© 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. 12392
    Prev
    Next
    INDEX
    Explanations

    boolean values and code identifiers

    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
    ØŃÙĬÙĨ
    -0.08
    notated
    -0.07
    uerta
    -0.07
    ä¸ĭå®ļ
    -0.07
    ä¸ĭåIJĮ
    -0.06
    ebut
    -0.06
    书åIJ§
    -0.06
    chand
    -0.06
     confi
    -0.06
    ÙħاÙħ
    -0.06
    POSITIVE LOGITS
    emplate
    0.07
    æĿ¥äºº
    0.06
    essar
    0.06
    ellis
    0.06
     slaughter
    0.06
    ாள
    0.06
    ably
    0.06
    饺
    0.06
    Ops
    0.06
    èĩĬ
    0.06
    Activations Density 0.019%

    No Known Activations