© 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. 23295
    Prev
    Next
    INDEX
    Explanations

    solving equations for variables

    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
    æŶä¸įæŶ
    -0.08
     PLACE
    -0.07
    arco
    -0.07
    cad
    -0.07
     Platz
    -0.06
    pton
    -0.06
    ç»ı常æĢ§
    -0.06
    æŁIJä¸Ģ天
    -0.06
    Receipt
    -0.06
     plus
    -0.06
    POSITIVE LOGITS
    åݻ买
    0.08
     Hend
    0.08
    loe
    0.08
    داد
    0.07
     Bod
    0.07
    icch
    0.07
    keh
    0.07
    eper
    0.07
    å¤ļæīį
    0.07
    sic
    0.07
    Activations Density 0.054%

    No Known Activations