© 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. 12386
    Prev
    Next
    INDEX
    Explanations

    with active surveillance

    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
    fort
    -0.08
    het
    -0.08
    æĭīå¼Ģ
    -0.07
    -reply
    -0.07
    teria
    -0.07
    olt
    -0.07
    terie
    -0.07
    iant
    -0.07
    寮
    -0.07
    alte
    -0.07
    POSITIVE LOGITS
    åijĬ
    0.07
    ommer
    0.07
    ä¸įæķ£
    0.07
    tanda
    0.07
     Tough
    0.07
    ä¸įå°ij人
    0.07
     tár
    0.07
    оÑģÑĤи
    0.06
    äh
    0.06
    çī¹åĪ«
    0.06
    Activations Density 0.118%

    No Known Activations