© 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. 48771
    Prev
    Next
    INDEX
    Explanations

    education, files, ribbon, machine, information, insights, appeal, literature, judge, educators

    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
    йл
    -0.08
    getStore
    -0.08
    æľ¨åħ°
    -0.08
    ãĨ
    -0.08
    ¹Ħ
    -0.08
     Britt
    -0.07
    haal
    -0.07
    θά
    -0.07
    å°Ķå¤ļ
    -0.07
    ientos
    -0.07
    POSITIVE LOGITS
    æŃ£ç¡®ä½¿çĶ¨
    0.07
    LO
    0.06
    大æĪĺ
    0.06
    æ´»çļĦ
    0.06
     hitt
    0.06
    åĢĴ
    0.06
    å¤§åľ°
    0.06
    æĥł
    0.06
    ÙĦس
    0.06
     deserved
    0.06
    Activations Density 0.997%

    No Known Activations