© 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. 37869
    Prev
    Next
    INDEX
    Explanations

    list of data structures

    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
    åį
    -0.07
    1
    -0.07
    asy
    -0.06
    ä¸įå¦Ĥ
    -0.06
    æĶĺ
    -0.06
    éĢIJ
    -0.06
    ache
    -0.06
    if
    -0.06
    A
    -0.06
    5
    -0.06
    POSITIVE LOGITS
    _PRIORITY
    0.08
    æ´»çļĦ
    0.08
    ivio
    0.08
    aveur
    0.08
     sortable
    0.08
    صاÙĦ
    0.08
    ÙĦÙģ
    0.08
    ãĥĹãĥ©ãĤ¤
    0.08
    çł´æµª
    0.08
    Painter
    0.08
    Activations Density 0.049%

    No Known Activations