© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17816
    Prev
    Next
    INDEX
    Explanations

    equation derivatives

    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
    aning
    -0.07
    å·¥ä½ľå§Ķåijĺä¼ļ
    -0.06
    -specific
    -0.06
    uster
    -0.06
    åıijçĶŁè¿ĩ
    -0.06
    ä¹ĭçªĹ
    -0.05
    zal
    -0.05
     undergoing
    -0.05
    jong
    -0.05
    污水å¤ĦçIJĨåİĤ
    -0.05
    POSITIVE LOGITS
    edin
    0.09
    æ¯Ķäºļ
    0.09
    ikov
    0.08
    essa
    0.08
    ãĥŀãĥ¼ãĤ¯
    0.08
    uccio
    0.08
    оÑģÑĤÑĢе
    0.08
     Accomp
    0.07
    chnik
    0.07
     Middleton
    0.07
    Activations Density 0.002%

    No Known Activations