© 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. 18965
    Prev
    Next
    INDEX
    Explanations

    point of view

    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è¦ģ
    -0.11
    æīĢ以ä»ĸ们
    -0.11
    æīĢ以ä»ĸ
    -0.11
    äºİæĺ¯ä»ĸ
    -0.11
    æīĢ以就
    -0.10
    çĦ¶èĢĮåľ¨
    -0.10
    æŶå°Ĩ
    -0.09
    ä½Ĩèĩ³å°ij
    -0.09
    æīĢ以她
    -0.09
    æīĢ以æĪij们
    -0.09
    POSITIVE LOGITS
    ï¼Į
    0.16
    ,
    0.14
    ØĮ
    0.13
    ï¼ĮãĢĬ
    0.10
    ,',
    0.09
    .,
    0.09
    ï¼Į“
    0.09
    áģĬ
    0.08
    ,.
    0.08
    ,<
    0.08
    Activations Density 0.023%

    No Known Activations