© 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. 38377
    Prev
    Next
    INDEX
    Explanations

    ôse decrees

    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
     âĢ¦.
    -0.08
    Âł
    -0.07
    ero
    -0.07
    æ»Ķ
    -0.07
    éķ¿ä¹ħ
    -0.07
    anes
    -0.07
    é©°
    -0.07
    à¤Ĥस
    -0.07
     latter
    -0.07
    pect
    -0.06
    POSITIVE LOGITS
    $$
    0.07
    èĭ¥å¹²éĹ®é¢ĺçļĦ
    0.07
     '$
    0.07
    	ext
    0.07
    $l
    0.07
    ÑĤаки
    0.07
    åĬ£
    0.06
    $b
    0.06
    gica
    0.06
    жÑĮ
    0.06
    Activations Density 0.001%

    No Known Activations