© 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. 10964
    Prev
    Next
    INDEX
    Explanations

    "as" followed by certain words

    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
    æīĢ以ä»ĸ
    -0.10
    æķħ
    -0.10
    æķħåIJį
    -0.10
    æīĢ以æĪij们
    -0.10
    åĽłæѤ
    -0.09
     поÑįÑĤомÑĥ
    -0.09
    æīĢ以å½ĵ
    -0.09
    æīĢ以她
    -0.08
     therefore
    -0.08
    æķħèĢĮ
    -0.08
    POSITIVE LOGITS
    åĽłä¸ºåľ¨
    0.13
    åĽłä¸ºè¿Ļ
    0.13
    æ¯ķç«Ł
    0.12
    åĽłä¸ºå®ĥ
    0.11
    åĽłä¸ºå®ĥ们
    0.11
    ãģ¨ãģĦãģĨãģ®ãĤĤ
    0.11
    åĽłä¸ºè¿Ļ个
    0.11
    è¿Ļå°Ĩ
    0.11
    åĽłçĤº
    0.11
    åĽłä¸º
    0.11
    Activations Density 0.422%

    No Known Activations