© 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. 39644
    Prev
    Next
    INDEX
    Explanations

    angle change

    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
    è¿ĺä¸į
    -0.08
    ceeded
    -0.08
    æĮ¯
    -0.08
    å©¿
    -0.07
    AndGet
    -0.07
    æĸŃ
    -0.07
    undai
    -0.07
    erb
    -0.07
    éĤĦä¸į
    -0.07
    ÙĪÙĨد
    -0.07
    POSITIVE LOGITS
     unchanged
    0.10
    åİŁæĿ¥æĺ¯
    0.09
    ä¿ĿæĮģä¸įåıĺ
    0.09
    åİŁæľī
    0.09
    çļĦæĶ¹åıĺ
    0.08
    åİŁæĿ¥
    0.08
    à¹Ģà¸Ķิม
    0.08
    åİŁåľ°
    0.08
    åİŁæĿ¥çļĦ
    0.08
    åİŁä¾Ĩ
    0.08
    Activations Density 0.105%

    No Known Activations