© 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. 31025
    Prev
    Next
    INDEX
    Explanations

    cyclic, lactols, imiphosphorane, carboxylic acids

    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
    éĢłæĪIJçļĦ
    -0.07
     unofficial
    -0.07
    éĢłæĪIJçļĦæįŁå¤±
    -0.07
     individually
    -0.07
     Goi
    -0.07
     reserves
    -0.06
    人次
    -0.06
     plen
    -0.06
    еÑĩаÑĤ
    -0.06
     recente
    -0.06
    POSITIVE LOGITS
    缸åºĶ
    0.09
    缸åºĶçļĦ
    0.08
    缸æĩī
    0.08
     formation
    0.08
    ä¸Ĭæĸ°
    0.07
    仪
    0.07
     corresponding
    0.07
    ัà¹Īà¸Ļ
    0.07
    å°įæĩī
    0.07
    对åºĶ
    0.07
    Activations Density 0.010%

    No Known Activations