© 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. 27855
    Prev
    Next
    INDEX
    Explanations

    external links and references

    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
     tramp
    -0.07
    ãĤ¹ãĥ¡
    -0.07
    tah
    -0.06
    åģı
    -0.06
    olazione
    -0.06
    è¡¢
    -0.06
    人头
    -0.06
    zerw
    -0.06
    çİĭä¹ĭ
    -0.06
     háb
    -0.06
    POSITIVE LOGITS
    æĺ¯åĽ½å®¶
    0.07
    anta
    0.07
    anes
    0.07
    nga
    0.07
    æĥ³æĿ¥
    0.07
    ions
    0.07
    éĸij
    0.07
    viso
    0.07
    ³³
    0.06
    JA
    0.06
    Activations Density 0.212%

    No Known Activations