© 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. 63489
    Prev
    Next
    INDEX
    Explanations

    numbers and lists following "Next"

    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
    ä¸Ģæĸij
    -0.07
    Ľ
    -0.06
    åĸĦ
    -0.06
    ä»İ严
    -0.06
     span
    -0.06
    ê°ģ
    -0.06
    举
    -0.05
    \
    -0.05
    éĹ·
    -0.05
    积
    -0.05
    POSITIVE LOGITS
    uelas
    0.08
    æīĵå¼Ģæīĭæľº
    0.08
    ikal
    0.07
    áĥĶáĥłáĥĺ
    0.07
    å®īä¿¡
    0.07
    ä¸ĭä¸ĢæĿ¡
    0.07
    ãĥ¼ãĥŀ
    0.07
     investe
    0.07
    "text
    0.07
    aret
    0.07
    Activations Density 0.015%

    No Known Activations