© 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. 3666
    Prev
    Next
    INDEX
    Explanations

    spin states or particles

    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
    ä¸įåıĬ
    -0.07
    çĴIJ
    -0.07
    ä¸įèĪį
    -0.07
    баÑĤ
    -0.07
    èıģ
    -0.07
    æ·ĺ
    -0.07
    碱
    -0.07
     pani
    -0.07
    иÑĤоÑĢ
    -0.07
    -Sah
    -0.07
    POSITIVE LOGITS
    åľ¨èº«
    0.08
     ruling
    0.07
    /angular
    0.07
    imensional
    0.07
     angular
    0.07
     spin
    0.07
    Assignable
    0.07
     spins
    0.07
    obe
    0.07
    omitempty
    0.07
    Activations Density 0.004%

    No Known Activations