© 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. 1450
    Prev
    Next
    INDEX
    Explanations

    rounding to decimal places or precision

    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
    åĩį
    -0.08
     deliberately
    -0.07
    ry
    -0.07
    ż
    -0.07
     freeze
    -0.07
    æ¬
    -0.07
    åĨ»
    -0.07
    é»ĺ认
    -0.07
    åı¹
    -0.07
    ä»ħæѤ
    -0.07
    POSITIVE LOGITS
    طة
    0.08
    ÙĨÙĩ
    0.08
    _ur
    0.08
     beis
    0.07
    psilon
    0.07
    achers
    0.07
    numeric
    0.07
    ottie
    0.07
    \\\\
    0.07
    anitize
    0.07
    Activations Density 0.002%

    No Known Activations