© 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. 1725
    Prev
    Next
    INDEX
    Explanations

    Delta symbols and mathematical notation

    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
     tro
    -0.06
    вÑĢа
    -0.06
    дÑĢав
    -0.06
    çķ
    -0.06
     carr
    -0.06
    滨海æĸ°åĮº
    -0.06
    å°Ĩå°±
    -0.06
    带
    -0.06
    imed
    -0.06
    .emit
    -0.06
    POSITIVE LOGITS
    ssa
    0.07
    quê
    0.07
    åĬłæĭ¿å¤§çļĦ
    0.07
    æĭįçļĦ
    0.07
    ä¹IJä¹İ
    0.07
    calculate
    0.07
    ULAR
    0.07
    ä¸ĩäºĭ
    0.07
    ä¸ĭè§Ĵ
    0.07
    Computed
    0.07
    Activations Density 0.110%

    No Known Activations