© 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. 31445
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols or abbreviations

    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
    egue
    -0.08
    acular
    -0.07
    acula
    -0.07
     socios
    -0.07
    注æĦıäºĨ
    -0.07
     føl
    -0.07
    亲身
    -0.07
    æıIJè¦ģ
    -0.07
    ä¸ĢåºĶ
    -0.07
    车çĶ¨
    -0.07
    POSITIVE LOGITS
    åģĩ
    0.07
    ëŀĢ
    0.07
    Ç
    0.07
    æ¹Ľ
    0.07
    áz
    0.07
    éķ¿åģĩ
    0.06
    åķ¥
    0.06
     hart
    0.06
    æŁIJ个
    0.06
    ither
    0.06
    Activations Density 0.042%

    No Known Activations