© 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. 48596
    Prev
    Next
    INDEX
    Explanations

    orderings/introductions of noun phrases

    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
    å¯Įæ°ij
    -0.09
    ilih
    -0.08
    첩
    -0.08
    ä¸Ģ缴å¾Ī
    -0.08
    bey
    -0.08
    sembler
    -0.08
    keb
    -0.07
    ä¹Łæĺ¯åįģåĪĨ
    -0.07
    汽水
    -0.07
     гидÑĢо
    -0.07
    POSITIVE LOGITS
    baum
    0.07
    绵
    0.07
    æĢł
    0.07
    isch
    0.07
    æĪijä¸įæķ¢
    0.07
    idis
    0.06
    etti
    0.06
    è¿Ļæĺ¯æĪij
    0.06
     counted
    0.06
    infeld
    0.06
    Activations Density 0.002%

    No Known Activations