© 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. 50050
    Prev
    Next
    INDEX
    Explanations

    PR branch, downshift, tutorial folder, payin, analysis directory, wrapping section, plugin directory, tunnel ingress

    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
    åĪĺæĸĩ
    -0.06
    åĽłäºº
    -0.06
     bos
    -0.06
    å³¥
    -0.06
    ä¹ĭ以
    -0.06
    人æĢ§åĮĸ
    -0.05
    碰ä¸Ĭ
    -0.05
    Say
    -0.05
    æĸ°ä¸ĸ纪
    -0.05
    assi
    -0.05
    POSITIVE LOGITS
    为äºĨæĸ¹ä¾¿
    0.09
    åıijçĶŁæŶ
    0.09
    ujan
    0.08
    è¿ĩç¨ĭä¸ŃçļĦ
    0.08
    trand
    0.08
    رÙĬÙĤ
    0.08
    quisite
    0.08
    opyright
    0.07
    oji
    0.07
    ä¼ģä¸ļèģĮå·¥
    0.07
    Activations Density 0.210%

    No Known Activations