© 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. 51671
    Prev
    Next
    INDEX
    Explanations

    cycles or loops

    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
    idd
    -0.08
    æĬĢå·§
    -0.06
    qualified
    -0.06
     plunged
    -0.06
    åĪĨæī¹
    -0.06
    roe
    -0.06
    gate
    -0.06
    æİĢèµ·
    -0.06
    æļ
    -0.06
    ibur
    -0.06
    POSITIVE LOGITS
    éĹŃçݯ
    0.14
    循çݯ
    0.14
     cycle
    0.13
     loop
    0.12
    -loop
    0.12
    循çĴ°
    0.12
     Cycle
    0.11
    loop
    0.11
    -cycle
    0.11
    cycle
    0.11
    Activations Density 0.065%

    No Known Activations