© 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. 28466
    Prev
    Next
    INDEX
    Explanations

    is... ?

    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
    à¸Īà¹īา
    -0.07
     gjerne
    -0.07
    uraa
    -0.06
    åı¯èĥ½çļĦ
    -0.06
    rš
    -0.06
    {}.
    -0.06
    å¾Īåı¯èĥ½
    -0.06
    !<
    -0.06
    !).
    -0.06
     whichever
    -0.06
    POSITIVE LOGITS
    çļĦåIJĹ
    0.17
    æĪijåIJĹ
    0.15
    )?
    0.14
    æĬijæĪĸ
    0.14
    ]?
    0.14
    "?
    0.13
    ))?
    0.13
    ï¼Ł
    0.13
    ï¼ŁãĢį
    0.13
    '?
    0.13
    Activations Density 0.595%

    No Known Activations