© 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. 1927
    Prev
    Next
    INDEX
    Explanations

    extreme intensity heat plasma vacuum

    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
    è¾ĥéķ¿
    -0.09
    ạch
    -0.08
    ÏĢÏī
    -0.08
    å±ħæĺĵ
    -0.08
    æľĢéķ¿
    -0.08
    ýt
    -0.08
    çľĭ好
    -0.08
    ரா
    -0.08
    è¾ĥéķ¿çļĦ
    -0.07
     jár
    -0.07
    POSITIVE LOGITS
     millions
    0.09
     conditions
    0.08
     cosmic
    0.08
     billions
    0.08
    åīįæīĢæľª
    0.08
    æŀģé«ĺ
    0.08
     immense
    0.08
    æķ°çĻ¾ä¸ĩ
    0.08
     high
    0.08
     extraordinary
    0.07
    Activations Density 0.018%

    No Known Activations