© 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. 32874
    Prev
    Next
    INDEX
    Explanations

    architectural lighting iconic images starts with

    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
     **
    -0.11
    à¥į
    -0.09
    åĬŁäºİ
    -0.07
    **
    -0.07
    Ìģ
    -0.07
    anova
    -0.07
    thon
    -0.07
    ategorie
    -0.06
    ategori
    -0.06
    trer
    -0.06
    POSITIVE LOGITS
    amment
    0.07
     "-//
    0.07
    åĤ¢
    0.07
    [*
    0.07
     <+
    0.06
     Nett
    0.06
    ..."
    0.06
    inol
    0.06
    адÑĮ
    0.06
    ...]
    0.06
    Activations Density 0.010%

    No Known Activations