© 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. 41643
    Prev
    Next
    INDEX
    Explanations

    events and concepts

    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
     αÏħÏĦά
    -0.07
    orda
    -0.06
     themselves
    -0.06
    ä¸Ģ个åı«
    -0.06
    itter
    -0.06
    æł¹æį®åħ¶
    -0.06
    TRUE
    -0.06
    åħħå®ŀèĩªå·±
    -0.06
    som
    -0.06
    iori
    -0.06
    POSITIVE LOGITS
    (s
    0.13
    (es
    0.11
    ÑĬÑĤ
    0.09
     extraordinaire
    0.09
    ry
    0.08
     |–
    0.08
    ä¹ĭ称çļĦ
    0.08
    -wise
    0.08
    [s
    0.08
    swith
    0.07
    Activations Density 1.028%

    No Known Activations