© 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. 63859
    Prev
    Next
    INDEX
    Explanations

    differences, mutate, slowed

    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
    ä¹ĭ缮çļĦ
    -0.09
    ิà¹īà¸Ļ
    -0.09
    åįĥèIJ¬
    -0.08
    åį«çĶŁåĴĮ
    -0.08
    åºĶ注æĦı
    -0.08
    istik
    -0.08
    å¦Ĥæŀľåıijçİ°
    -0.08
     chừng
    -0.08
    emplates
    -0.08
    第ä¸Ģç¯ĩ
    -0.08
    POSITIVE LOGITS
    åħ¶æ¬¡æĺ¯
    0.09
     plus
    0.09
    èĢĮä¸Ķ
    0.08
    使å¾Ĺ
    0.08
    åĬłä¹ĭ
    0.08
    缺å°ij
    0.08
    åħ¶æ¬¡
    0.08
    lack
    0.08
     Moreover
    0.08
     combined
    0.08
    Activations Density 0.012%

    No Known Activations