© 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. 40724
    Prev
    Next
    INDEX
    Explanations

    .js or name endings

    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
     dint
    -0.07
    ophon
    -0.07
    ABL
    -0.07
    æķĪ
    -0.07
    æµİ
    -0.07
    ¼
    -0.07
    LOSS
    -0.07
    è¸ıè¸ıå®ŀå®ŀ
    -0.07
    LOT
    -0.07
    ä¹ĭäºĮ
    -0.07
    POSITIVE LOGITS
     cre
    0.08
    åħĪ导
    0.08
    laje
    0.07
    ingham
    0.07
    ³
    0.07
    аз
    0.07
    é¹ı
    0.07
    azol
    0.07
    forums
    0.07
    ingers
    0.07
    Activations Density 0.008%

    No Known Activations