© 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. 15163
    Prev
    Next
    INDEX
    Explanations

    related to 's properties

    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
    ering
    -0.08
    ical
    -0.07
    å¾Īéķ¿çļĦ
    -0.07
    å¾Īå¤ļæŶåĢĻ
    -0.07
     ÙħØ°
    -0.07
    ashi
    -0.07
    许å¤ļçļĦ
    -0.07
    å¾Ģ常
    -0.07
    ulk
    -0.07
    åı¯èĥ½ä¼ļæľī
    -0.07
    POSITIVE LOGITS
    åıĭæĥħéĵ¾æİ¥
    0.07
    ÙĪÙĨد
    0.07
    ä¹ĭåĽ½
    0.06
    IRA
    0.06
    æģ°
    0.06
    tenham
    0.06
     коÑĤоÑĢого
    0.06
    ä¸Ĭè¿Ľå¿ĥ
    0.06
    人åħ¬
    0.06
    otrop
    0.06
    Activations Density 0.022%

    No Known Activations