© 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. 20838
    Prev
    Next
    INDEX
    Explanations

    friends and family relationships

    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
    gnore
    -0.08
    çĪ¸å¦Ī
    -0.08
    ç¥ĸå®Ĺ
    -0.08
    åĵªæľī
    -0.08
    åĨįæİ¥åĨį
    -0.08
    çıŃä¼ļ
    -0.08
    çĪ¸çĪ¸å¦Īå¦Ī
    -0.08
    ä¸Ģå¾ĭ
    -0.07
    ä¸ĵ家æĮĩåĩº
    -0.07
    以赴
    -0.07
    POSITIVE LOGITS
    åIJĮ为
    0.09
    å½ĵæŶ
    0.08
    åIJ¯
    0.08
     influential
    0.08
    æıIJæIJº
    0.08
     mutual
    0.08
    交éĽĨ
    0.08
    å½ĵæŶçļĦ
    0.08
    æľī好
    0.07
     adm
    0.07
    Activations Density 0.826%

    No Known Activations