© 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. 33364
    Prev
    Next
    INDEX
    Explanations

    systems, organs, tissues, products

    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
    ringer
    -0.08
    ç´°
    -0.08
    anni
    -0.07
    finity
    -0.07
     Fine
    -0.07
    ç»Ĩèħ»
    -0.07
    aud
    -0.07
    æ¯ı家
    -0.07
    enius
    -0.07
    ä¸ĢåºĶ
    -0.07
    POSITIVE LOGITS
    æķ´ä½ĵçļĦ
    0.16
    æķ´ä½ĵ
    0.14
     whole
    0.13
    æķ´ä½ĵä¸Ĭ
    0.13
    æķ´ä¸ª
    0.13
     entire
    0.13
    çļĦæķ´ä½ĵ
    0.12
    æķ´é«Ķ
    0.12
    æķ´æľº
    0.11
    whole
    0.11
    Activations Density 0.221%

    No Known Activations