© 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. 22706
    Prev
    Next
    INDEX
    Explanations

    geometric curvature

    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
    大éĻ¢
    -0.08
    -schema
    -0.07
     Shades
    -0.07
    çĶµåŃIJåħĥåĻ¨ä»¶
    -0.07
    asley
    -0.07
     trickle
    -0.07
    缴æİ¥æĪĸéĹ´æİ¥
    -0.07
    羽翼
    -0.07
    çĤİçĤİ
    -0.07
    çľŁç©º
    -0.07
    POSITIVE LOGITS
     curvature
    0.12
    -cur
    0.10
    æĽ²
    0.09
    å¼¯æĽ²
    0.08
    cur
    0.08
     bezier
    0.08
    curve
    0.08
    æĽ²çº¿çļĦ
    0.08
    ç¼Ĩ
    0.08
    (cur
    0.08
    Activations Density 0.006%

    No Known Activations