© 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. 19464
    Prev
    Next
    INDEX
    Explanations

    spectroscopic ton pump inhibitors

    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
     Monteiro
    -0.08
    adÃŃ
    -0.08
    ighborhood
    -0.08
    vila
    -0.08
    åħ¨ä½ĵä¼ļè®®
    -0.08
    ÑĢоÑĤ
    -0.07
    ì·¨
    -0.07
    avor
    -0.07
    ynd
    -0.07
    hiri
    -0.07
    POSITIVE LOGITS
     +
    0.07
    procs
    0.07
    人ä¸Ń
    0.06
    +
    0.06
    AttributeName
    0.06
     onstage
    0.06
    ä¸Ģç²Ĵ
    0.06
    ernet
    0.06
    æķ°çĽ®
    0.06
    ÙĪاÙĨ
    0.06
    Activations Density 0.001%

    No Known Activations