© 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. 19333
    Prev
    Next
    INDEX
    Explanations

    replicates, alkoxylates, additions

    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
     hardcoded
    -0.08
    ImageUrl
    -0.07
    èµ°åĩºåİ»
    -0.07
    éľ²æ°´
    -0.07
    Outlet
    -0.07
     switch
    -0.07
     outlet
    -0.07
    istor
    -0.07
    åĩºåĽ½çķĻåѦ
    -0.07
    åįĬå¹´çļĦ
    -0.06
    POSITIVE LOGITS
     additional
    0.10
    åı¯ä»¥å¢ŀåĬł
    0.09
    additional
    0.09
    éĽį
    0.09
     thêm
    0.09
    é¢Ŀå¤ĸçļĦ
    0.09
    Additional
    0.08
     additions
    0.08
    éĻĦåĬł
    0.08
     extras
    0.08
    Activations Density 0.017%

    No Known Activations