© 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. 8444
    Prev
    Next
    INDEX
    Explanations

    only

    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
    dings
    -0.10
    æĸ°åĬłåĿ¡
    -0.10
    çĽ¸ä¼¼æĸĩçĮ®
    -0.10
    reopen
    -0.09
     tamp
    -0.09
    holt
    -0.09
    ÙĨÙĩ
    -0.09
    ity
    -0.09
    stroy
    -0.09
    èĻ½çĦ¶æľī
    -0.09
    POSITIVE LOGITS
    à¹Ĩ
    0.08
    æĪijä¸Ģ个人
    0.07
    éĻIJäºİ
    0.07
    ÏĤ
    0.07
    o
    0.07
    ×ķ
    0.06
    åIJ¬è¯´è¿ĩ
    0.06
    å±ĢéĻIJäºİ
    0.06
     à¹Ĩ
    0.06
     wenige
    0.06
    Activations Density 0.001%

    No Known Activations