© 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. 21190
    Prev
    Next
    INDEX
    Explanations

    section/article 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
    çĮĽ
    -0.06
    伦
    -0.06
    æºľ
    -0.06
    менно
    -0.06
    /math
    -0.06
     pli
    -0.06
    ฤ
    -0.06
    æĺ
    -0.06
     stuck
    -0.06
    æŃ£æĺ¯åĽłä¸º
    -0.06
    POSITIVE LOGITS
    第ä¸ī款
    0.09
    ä¿Ŀéļľ
    0.08
    andid
    0.08
    หà¸Ļึà¹Īà¸ĩà¸Ĥà¸Ńà¸ĩ
    0.08
    第ä¸Ģ款
    0.08
    ä¿Ŀéļľæݪæĸ½
    0.08
    abinet
    0.08
    ç·ł
    0.08
    wal
    0.07
    afka
    0.07
    Activations Density 0.062%

    No Known Activations