© 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. 32475
    Prev
    Next
    INDEX
    Explanations

    legal questions or recourse

    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
    æĸ¹åľĨ
    -0.07
    ÐĴÐĶ
    -0.07
    空空
    -0.06
    碾
    -0.06
    åIJĮåIJį
    -0.06
    ืà¹īà¸Ń
    -0.06
    ãĤ¤ãĤº
    -0.06
    æĹłåīį
    -0.06
    举è¡Ĺ
    -0.06
    byte
    -0.06
    POSITIVE LOGITS
    likely
    0.08
     regarding
    0.08
     likely
    0.07
    路桥
    0.07
     Regarding
    0.07
    nat
    0.07
    ldr
    0.07
     typically
    0.07
    ccoli
    0.07
    è§ĤçĤ¹åĴĮ
    0.07
    Activations Density 0.071%

    No Known Activations