© 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. 27825
    Prev
    Next
    INDEX
    Explanations

    array of data structures

    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
    ëģĶ
    -0.13
    ardini
    -0.10
    tingham
    -0.09
    åIJĪãģĦ
    -0.09
    ideshow
    -0.09
    brero
    -0.09
    umente
    -0.09
     adanya
    -0.08
    zelf
    -0.08
    erma
    -0.08
    POSITIVE LOGITS
    ÚĨÙĩ
    0.09
    ÑĩаÑĤ
    0.09
    ments
    0.08
    -wide
    0.08
    ette
    0.07
    ially
    0.07
    wide
    0.07
    psilon
    0.07
    angement
    0.07
    ÙĪاج
    0.07
    Activations Density 0.062%

    No Known Activations