© 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. 56483
    Prev
    Next
    INDEX
    Explanations

    mathematics and algebra concepts

    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
    -0.08
     Cola
    -0.06
    åı®
    -0.06
     "
    -0.06
    å¼Ĥ
    -0.06
     McB
    -0.06
    istributed
    -0.06
    ä¸īåı£
    -0.06
    âħ
    -0.06
     Amat
    -0.05
    POSITIVE LOGITS
    ç½ijç«Ļ导èĪª
    0.09
    transition
    0.09
    Transition
    0.09
    -navigation
    0.09
     PDIP
    0.08
    atoires
    0.08
    管æīĢ
    0.08
     tránsito
    0.08
    actly
    0.08
    -tool
    0.08
    Activations Density 0.020%

    No Known Activations