© 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. 31535
    Prev
    Next
    INDEX
    Explanations

    fractional exponents

    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
    éºŁ
    -0.09
    çĴŀ
    -0.08
    @[
    -0.08
    eker
    -0.08
    лона
    -0.08
    riers
    -0.08
    oroz
    -0.07
    ¤íŀ
    -0.07
    ç»®
    -0.07
    ILT
    -0.07
    POSITIVE LOGITS
    è¿ĺæĺ¯
    0.07
    ç¥ĸå®Ĺ
    0.07
    ou
    0.07
    1
    0.07
    æį£
    0.06
    _merge
    0.06
    _tracking
    0.06
    -reviewed
    0.06
     marking
    0.06
    on
    0.06
    Activations Density 0.006%

    No Known Activations