© 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. 42766
    Prev
    Next
    INDEX
    Explanations

    comparing quantities

    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
    ä¸Ńéĥ¨
    -0.08
    æĥ³å¾ĹåĪ°
    -0.07
    osa
    -0.07
    Popular
    -0.07
    æµģè¡ĮçļĦ
    -0.07
     Popular
    -0.07
    çļĦéĩįè¦ģåİŁåĽł
    -0.06
    å½ĵéĿ¢
    -0.06
    è¢
    -0.06
     popular
    -0.06
    POSITIVE LOGITS
     közül
    0.10
    åĶ¯ä¸Ģä¸Ģ个
    0.09
    .none
    0.08
    äºijé£ŀ
    0.08
    udev
    0.08
    undry
    0.08
     ëĤĺ머
    0.08
    ayne
    0.08
    æĺ¯åĶ¯ä¸Ģ
    0.08
     none
    0.08
    Activations Density 0.101%

    No Known Activations