© 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. 1229
    Prev
    Next
    INDEX
    Explanations

    code structure `.body`, `.calls`, `dependencies`, `threads`

    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
    rome
    -0.09
    uttle
    -0.07
    antha
    -0.07
    onar
    -0.07
    Sharper
    -0.06
    .exports
    -0.06
    ä»ĸæľī
    -0.06
    strate
    -0.06
    /server
    -0.06
    enix
    -0.06
    POSITIVE LOGITS
     collectively
    0.11
    ä¹ĭä¸ĢçļĦ
    0.10
    =[]
    0.09
     allemaal
    0.09
    约èĢĮåIJĮ
    0.09
     []*
    0.08
    åħ¨éĥ¨éĥ½
    0.08
     ÙĥÙĦÙĩا
    0.08
    ä¸ŃçļĦæīĢæľī
    0.08
    åħ¨éĥ¨
    0.08
    Activations Density 0.187%

    No Known Activations