© 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. 30639
    Prev
    Next
    INDEX
    Explanations

    formation of products

    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
    è´ŀ
    -0.08
    ë´ī
    -0.08
    æī¦
    -0.08
    egu
    -0.07
    .stdin
    -0.07
    amana
    -0.06
    wein
    -0.06
     répar
    -0.06
    ÙĤض
    -0.06
    _working
    -0.06
    POSITIVE LOGITS
     generated
    0.09
    ACHED
    0.09
     formed
    0.08
    çļĦ产çĶŁ
    0.08
     accumulating
    0.07
    ä¸īæĹł
    0.07
     created
    0.07
     vznik
    0.07
    :create
    0.07
     produced
    0.07
    Activations Density 0.004%

    No Known Activations