© 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. 63037
    Prev
    Next
    INDEX
    Explanations

    partial differential equation

    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
    iÅĤ
    -0.08
    nees
    -0.07
     frequ
    -0.07
    à§ĭধ
    -0.07
    åłĤçļĩ
    -0.07
    Ñħе
    -0.07
    ryp
    -0.07
    èį¡èį¡
    -0.07
    ¾
    -0.07
    çݯ线
    -0.06
    POSITIVE LOGITS
    sWith
    0.08
    ities
    0.08
    ãĤ´ãĥ¼
    0.08
    ITIES
    0.08
    imensional
    0.07
    Ñĥ
    0.07
     governing
    0.07
    о
    0.07
    们
    0.07
    است
    0.07
    Activations Density 0.002%

    No Known Activations