© 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. 16054
    Prev
    Next
    INDEX
    Explanations

    listing items separated by commas or "and"

    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
    ness
    -0.10
    pson
    -0.09
    wise
    -0.08
    çıij
    -0.08
    ä¾£
    -0.08
    ĻĤ
    -0.08
    à§įত
    -0.08
    berry
    -0.08
    koord
    -0.08
    nable
    -0.08
    POSITIVE LOGITS
    en
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.09
    ت
    0.08
    an
    0.08
    å°±
    0.08
    éī´äºİ
    0.08
    äºĨ
    0.08
    à¥ĩ
    0.07
    кÑĢа
    0.07
    enam
    0.07
    Activations Density 0.004%

    No Known Activations