© 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. 42094
    Prev
    Next
    INDEX
    Explanations

    exactly one

    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
    itech
    -0.07
    اÙģÙĦ
    -0.07
    .scal
    -0.07
    ffel
    -0.06
    ava
    -0.06
    aray
    -0.06
    chen
    -0.06
    join
    -0.06
    [__
    -0.06
    urch
    -0.06
    POSITIVE LOGITS
    æģ°å¥½
    0.10
    åĶ¯ä¸ĢçļĦ
    0.10
    à¹Ģà¸Ķียว
    0.10
     exactly
    0.09
    à¸ŀà¸Ńà¸Ķี
    0.09
    ä¸įå¤ļçļĦ
    0.08
    åįķä¸Ģ
    0.08
    ä»ħæľīçļĦ
    0.08
    (one
    0.08
    åĶ¯ä¸Ģ
    0.08
    Activations Density 0.014%

    No Known Activations