© 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. 48093
    Prev
    Next
    INDEX
    Explanations

    special characters and accented letters

    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
    ../../../
    -0.10
    usercontent
    -0.09
    ities
    -0.08
    ULER
    -0.08
    izontal
    -0.08
    å¹³æĺĵ
    -0.08
     latter
    -0.07
    áĥIJáĥĹ
    -0.07
    à§įত
    -0.07
    amiento
    -0.07
    POSITIVE LOGITS
    est
    0.08
    ·
    0.08
    ê¹IJ
    0.08
    atively
    0.07
     ÑĤаки
    0.07
    她表示
    0.07
    tures
    0.07
    latt
    0.07
    ï¸İ
    0.07
    çĦ¶å¤§
    0.07
    Activations Density 0.001%

    No Known Activations