© 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. 65038
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and present perfect states

    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
    æĬķèµĦæĪĸ
    -0.07
     sometimes
    -0.07
     Sometimes
    -0.07
     manchmal
    -0.07
    人æĪĸ
    -0.07
     anywhere
    -0.07
    нибÑĥдÑĮ
    -0.06
    åĥıä½ł
    -0.06
    ä¹Łåĥı
    -0.06
    ocol
    -0.06
    POSITIVE LOGITS
    æĥħåĨµè¯´æĺİ
    0.10
     reportedly
    0.10
    èµĦæĸĻæĺ¾ç¤º
    0.10
    å¾Īåı¯èĥ½
    0.09
     ê²Įëĭ¤ê°Ģ
    0.08
    kasten
    0.08
    主åĬ¨
    0.08
     navÃŃc
    0.08
    è°ĥæŁ¥æĺ¾ç¤º
    0.08
    æĺİç¡®çļĦ
    0.08
    Activations Density 0.024%

    No Known Activations