© 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. 48772
    Prev
    Next
    INDEX
    Explanations

    kron, tensor 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
    ãģ¾ãģĹãģ¦
    -0.09
    haft
    -0.08
    umbo
    -0.08
    ctors
    -0.08
    ÑĢек
    -0.07
    itage
    -0.07
    utton
    -0.07
     tá»ķn
    -0.07
    itzt
    -0.07
    ÐŀÐł
    -0.07
    POSITIVE LOGITS
     anything
    0.08
    anything
    0.08
    æľīçļĦ
    0.07
    DidLoad
    0.07
    age
    0.07
    istin
    0.07
    ÙĬد
    0.07
    ب
    0.07
     everything
    0.07
    armac
    0.07
    Activations Density 0.001%

    No Known Activations