© 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. 21792
    Prev
    Next
    INDEX
    Explanations

    quantitative measurement of concentration

    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
    ìĸ¸
    -0.08
    å½ĵäºĭ
    -0.07
     Canc
    -0.07
     hug
    -0.07
    ä¸ĢåĬ¨
    -0.07
    åįļ士åIJİ
    -0.07
    触è§ī
    -0.07
    åĬ¡åħ¬å¼Ģ
    -0.07
     Exclus
    -0.07
    zek
    -0.07
    POSITIVE LOGITS
     insol
    0.08
    æ£Ģåĩº
    0.07
    æł·åĵģ
    0.07
    被æµĭ
    0.07
    è¶ħæłĩ
    0.07
     adul
    0.07
    çħ§çĽ¸
    0.07
    æķŀ
    0.07
    æ£Ģæµĭç»ĵæŀľ
    0.07
     concentration
    0.07
    Activations Density 0.013%

    No Known Activations