© 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. 49808
    Prev
    Next
    INDEX
    Explanations

    page displays/cycles

    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
    æĹłäºĭ
    -0.08
    ãĥĭãĤ¢
    -0.07
    entic
    -0.07
    ä¸Ŀä¸Ŀ
    -0.07
    icks
    -0.07
    为ä»Ģä¹Īä¸į
    -0.06
    пок
    -0.06
    gers
    -0.06
    eprom
    -0.06
     prip
    -0.06
    POSITIVE LOGITS
     ÑģнаÑĩала
    0.10
    åħĪæĺ¯
    0.09
    æĪijåħĪ
    0.09
    äºĨä¸Ģ段
    0.09
     dahulu
    0.09
     followed
    0.09
     preceded
    0.08
     seguido
    0.08
    åħĪãģ«
    0.08
    åħĪæĿ¥
    0.08
    Activations Density 0.007%

    No Known Activations