© 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. 45454
    Prev
    Next
    INDEX
    Explanations

    numbers and specific items

    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
    ema
    -0.08
    ä¹ŁæĪIJäºĨ
    -0.08
    enho
    -0.07
    emark
    -0.07
    #${
    -0.07
    ÑģÑİ
    -0.07
    oko
    -0.07
    ETO
    -0.07
    cheid
    -0.07
    pling
    -0.07
    POSITIVE LOGITS
     ones
    0.15
     ÙħÙĨÙĩا
    0.14
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.13
     ervan
    0.13
     daarvan
    0.12
     deles
    0.12
    åħ¶ä¸ŃçļĦ
    0.11
     thereof
    0.11
    åħ¶ä¸Ń
    0.11
     delas
    0.10
    Activations Density 0.371%

    No Known Activations