© 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. 13819
    Prev
    Next
    INDEX
    Explanations

    liquid-liquid extraction

    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
    дено
    -0.08
    rome
    -0.07
    pto
    -0.07
    ä¸įæŃ»
    -0.07
    ä¸įæĭĶ
    -0.07
    å°Ħç¨ĭ
    -0.07
     Garan
    -0.07
    ansson
    -0.07
    çĪ¬è¡Į
    -0.07
    enzo
    -0.07
    POSITIVE LOGITS
     oil
    0.08
    åĪĨåĩº
    0.08
    èIJĥåıĸ
    0.08
     separation
    0.08
    åĪĨ离
    0.07
     Oil
    0.07
     oily
    0.07
    -separated
    0.07
    ubl
    0.07
     partition
    0.07
    Activations Density 0.019%

    No Known Activations