© 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. 56808
    Prev
    Next
    INDEX
    Explanations

    diamond rings

    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
    -0.08
     genuinely
    -0.07
    elen
    -0.07
    çĶŁäº§å»ºè®¾åħµåĽ¢
    -0.07
    æ±Łå®ģ
    -0.07
    èĤļåŃIJéĩĮ
    -0.07
     allegedly
    -0.07
    æģ¨ä¸įå¾Ĺ
    -0.07
    åĭĥåĭĥ
    -0.07
    ÙĪاÙħ
    -0.06
    POSITIVE LOGITS
    arre
    0.08
    è°Ń
    0.07
    ä¹Ŀ天
    0.07
    çļĦäºĭåĦ¿
    0.07
     hol
    0.07
    AGO
    0.07
    ï¼Ĭï¼Ĭ
    0.07
    æļĤ
    0.06
     tonight
    0.06
    åıĤ
    0.06
    Activations Density 0.153%

    No Known Activations