© 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. 39701
    Prev
    Next
    INDEX
    Explanations

    induced voltage or current

    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
    cach
    -0.08
    飬
    -0.07
    æīĭåĨĮ
    -0.07
    ach
    -0.07
    ä¸įæĹ©
    -0.06
    achine
    -0.06
    åĪļä¸Ģ
    -0.06
     cach
    -0.06
    illery
    -0.06
    ografi
    -0.06
    POSITIVE LOGITS
    -induced
    0.09
    æĦŁåºĶ
    0.08
    /cop
    0.08
     induced
    0.07
     induces
    0.07
    áĢķáĢº
    0.07
    èĨĺ
    0.07
    atz
    0.07
    -generated
    0.07
    /generated
    0.07
    Activations Density 0.003%

    No Known Activations