© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16315
    Prev
    Next
    INDEX
    Explanations

    something like this

    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
    upt
    -0.07
    isable
    -0.07
    ROID
    -0.07
    iores
    -0.07
    ìĤ¼
    -0.07
    éĩįçĶŁä¹ĭ
    -0.07
    urent
    -0.07
    lore
    -0.07
    åĪĩå®ŀæıIJé«ĺ
    -0.07
     notably
    -0.07
    POSITIVE LOGITS
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.09
    à¹Ģà¸Ķียวà¸ģัà¸Ļ
    0.09
    ï¼ļ
    0.09
     halnya
    0.08
    emente
    0.08
    vente
    0.08
     обÑĢазом
    0.07
    æīĢ示
    0.07
    orum
    0.07
    ìĶ©
    0.07
    Activations Density 0.037%

    No Known Activations