© 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. 30239
    Prev
    Next
    INDEX
    Explanations

    if, to, sometimes, two, with

    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
    鬣
    -0.08
    éģľ
    -0.06
    esian
    -0.06
    ä¸įä½İäºİ
    -0.06
    adi
    -0.06
    æĤī
    -0.06
    ationale
    -0.06
    á»ijng
    -0.06
    pedia
    -0.06
    麾
    -0.06
    POSITIVE LOGITS
    åıĪå¦Ĥ
    0.09
    åľ¨æŁIJ
    0.09
    ä¾ĭå¦Ĥ
    0.08
    riz
    0.08
    æŁIJ
    0.08
    ikit
    0.07
    éľĢè¦ģåIJĮ
    0.07
    ilder
    0.07
    幸è¿IJçļĦ
    0.07
     напÑĢимеÑĢ
    0.07
    Activations Density 0.029%

    No Known Activations