© 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. 46101
    Prev
    Next
    INDEX
    Explanations

    type or special character sequences

    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
     Doc
    -0.07
    åģļ好
    -0.06
    ook
    -0.06
    Doc
    -0.06
    æİĪæĿĥçļĦ
    -0.06
    пÑĢоÑģÑĭ
    -0.06
    ëŀĺ
    -0.06
    doc
    -0.06
     اÙĦÙĪ
    -0.06
    /
    -0.06
    POSITIVE LOGITS
    atel
    0.09
    ç¾İåĽ¾
    0.08
    ë¹Ļ
    0.08
    ä¸īåĪĨ
    0.08
    มà¸Ļ
    0.08
    anst
    0.08
    iori
    0.08
     ('$
    0.08
    arty
    0.07
    -anchor
    0.07
    Activations Density 0.009%

    No Known Activations