© 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. 60728
    Prev
    Next
    INDEX
    Explanations

    domain name

    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
    欢
    -0.08
    æļĸæ°Ķ
    -0.07
    çĮ®
    -0.07
     lean
    -0.07
    éĹ·
    -0.07
    è¢«ä¾ĽåºĶåķĨ
    -0.06
    éĥ¨éķ¿
    -0.06
    微信æī«ä¸Ģæī«
    -0.06
    çģ«çĤī
    -0.06
     induction
    -0.06
    POSITIVE LOGITS
    åŁŁåIJį
    0.14
    åIJİç¼Ģ
    0.11
     domain
    0.10
    _suffix
    0.10
     domains
    0.10
    domain
    0.10
    Domain
    0.10
     Domain
    0.09
     suffix
    0.09
    domains
    0.09
    Activations Density 0.131%

    No Known Activations