© 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. 18741
    Prev
    Next
    INDEX
    Explanations

    unique

    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
    ä¸ĢåĪ»
    -0.07
    æĭĸç´¯
    -0.07
    éģł
    -0.07
    ailer
    -0.07
    常温
    -0.07
    ä¼łäºº
    -0.06
    ÙĴÙĥ
    -0.06
    صÙĬ
    -0.06
    пÑĢÑı
    -0.06
    éĥ½ä¸įçĶ¨
    -0.06
    POSITIVE LOGITS
     uniqueness
    0.15
     uniquely
    0.13
    unique
    0.13
     unique
    0.12
     UNIQUE
    0.12
     Unique
    0.11
    åĶ¯ä¸ĢçļĦ
    0.11
    Unique
    0.11
    åĶ¯ä¸Ģ
    0.10
     uniqu
    0.10
    Activations Density 0.083%

    No Known Activations