© 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. 55709
    Prev
    Next
    INDEX
    Explanations

    quality

    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
    rah
    -0.08
    lege
    -0.07
    ä¸įåı¯æĢĿè®®
    -0.07
     salut
    -0.07
    æĸ¹ä¾¿
    -0.07
    à¸łà¸²à¸Ħ
    -0.07
    ån
    -0.07
    apon
    -0.07
    laki
    -0.07
    åd
    -0.07
    POSITIVE LOGITS
    -quality
    0.18
     quality
    0.17
    quality
    0.16
    Quality
    0.13
     Quality
    0.13
    è´¨éĩıçļĦ
    0.12
     каÑĩеÑģÑĤво
    0.12
     craftsmanship
    0.12
     каÑĩеÑģÑĤва
    0.11
    è´¨éĩı
    0.11
    Activations Density 0.288%

    No Known Activations