© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32944
    Prev
    Next
    INDEX
    Explanations

    lambda expression, nested, query, form

    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
    æīĭåı¯
    -0.07
    ãĤ«ãĥĥãĥĪ
    -0.07
     cra
    -0.07
    åĩŃ
    -0.07
    IFY
    -0.06
    ients
    -0.06
    å¦Ĥ鼨
    -0.06
    icht
    -0.06
    åIJĮæľŁçļĦ
    -0.06
    _poly
    -0.06
    POSITIVE LOGITS
    æ¯Ķè¾ĥå¤įæĿĤ
    0.11
    åµĮå¥Ĺ
    0.11
     nested
    0.10
     inside
    0.09
    _nested
    0.09
     внÑĥÑĤÑĢи
    0.09
    inside
    0.09
     Nested
    0.09
     denominator
    0.08
    Nested
    0.08
    Activations Density 0.010%

    No Known Activations