© 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. 14820
    Prev
    Next
    INDEX
    Explanations

    conjugation, transformation, transduction

    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
    æĶ¯æĴij
    -0.07
    çĸ²è½¯
    -0.06
    ront
    -0.06
    ç»ĦåIJĪ
    -0.06
    éĻįèĢĹ
    -0.06
    fol
    -0.06
    nolog
    -0.06
     folly
    -0.06
    大家åºŃ
    -0.06
    art
    -0.06
    POSITIVE LOGITS
    ä»ĭ
    0.10
     facilitated
    0.08
    ĶĦ
    0.08
    -mediated
    0.08
    ÙĪاس
    0.07
     arricch
    0.07
     bystand
    0.07
     mediated
    0.07
    IPHER
    0.07
    ugen
    0.07
    Activations Density 0.008%

    No Known Activations