© 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. 1401
    Prev
    Next
    INDEX
    Explanations

    number of people or beds

    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
     billions
    -0.12
    亿ä¸ĩ
    -0.09
     Millions
    -0.09
     millions
    -0.09
     trillion
    -0.08
    åįĥåįĥä¸ĩ
    -0.08
     jutaan
    -0.07
    ä¸ĩåħ¬éĩĮ
    -0.07
     milhões
    -0.07
    çĻ¾åĢį
    -0.07
    POSITIVE LOGITS
    人æķ°
    0.11
    è§Ħ模
    0.11
    人æķ°çļĦ
    0.10
    è§Ħ模çļĦ
    0.10
    è¦ı模
    0.09
    人æķ¸
    0.09
    éħįå¤ĩäºĨ
    0.08
    è§Ħ模为
    0.08
    éħįå¤ĩ
    0.08
    æłĩéħį
    0.08
    Activations Density 0.263%

    No Known Activations