© 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. 28759
    Prev
    Next
    INDEX
    Explanations

    activity, creation, and education

    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
    æķĻèĤ²åŁ¹è®Ń
    -0.07
    æķĻèĤ²åĴĮ
    -0.07
    ä¸ļçķĮ
    -0.07
    èĢĥè¯ķ大纲
    -0.07
    venience
    -0.07
    æĮĩæľĽ
    -0.06
    æķĻèĤ²ä¸İ
    -0.06
     ÐłÐ¾Ð¶
    -0.06
    bers
    -0.06
     Cursos
    -0.06
    POSITIVE LOGITS
    åħ¨çıŃ
    0.10
     classmates
    0.09
    holt
    0.09
    æ¯ı人
    0.09
     encouraged
    0.09
    å°ıç»Ħ
    0.09
    èĩªéĢī
    0.09
    åħ¨æł¡
    0.08
    åIJĮä¼´
    0.08
     brainstorm
    0.08
    Activations Density 0.098%

    No Known Activations