© 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. 27892
    Prev
    Next
    INDEX
    Explanations

    contact details and phone numbers

    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
    çĶ³è¯·èģĮä½į
    -0.08
    微信æī«çłģ
    -0.08
    mene
    -0.07
    éĺ¶
    -0.07
    èIJ¥ä¸ļåijĺ
    -0.07
    icensing
    -0.07
    à¸ĺà¸ĩ
    -0.07
    çļĦæľºä¼ļ
    -0.07
    æĪijçļĦçľĭæ³ķ
    -0.07
     Cabin
    -0.07
    POSITIVE LOGITS
     address
    0.12
     addresses
    0.11
    åľ°åĿĢ
    0.11
    èģĶç³»æĸ¹å¼ı
    0.11
    详ç»Ĩåľ°åĿĢ
    0.11
    address
    0.11
    /address
    0.10
     адÑĢеÑģ
    0.10
     адÑĢеÑģа
    0.10
     adress
    0.09
    Activations Density 0.230%

    No Known Activations