© 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. 18144
    Prev
    Next
    INDEX
    Explanations

    eigenvalue and energy calculation

    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
    stown
    -0.07
     aged
    -0.07
    èµĦæĸĻä¸ĭè½½
    -0.07
    skou
    -0.07
    erville
    -0.07
    .cm
    -0.07
    zilla
    -0.07
     STO
    -0.07
    عاÙĨ
    -0.07
    ikian
    -0.07
    POSITIVE LOGITS
    ahari
    0.07
    iteration
    0.07
     associated
    0.07
    åĶ¯ä¸Ģ
    0.07
     Texans
    0.07
    wart
    0.07
     tide
    0.07
     iteration
    0.07
     eigen
    0.06
    imestamp
    0.06
    Activations Density 0.005%

    No Known Activations