© 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. 39261
    Prev
    Next
    INDEX
    Explanations

    Hawaiian names, associate, joins team, new, part, number

    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
    è±ģ
    -0.07
    æIJIJ
    -0.07
    PY
    -0.07
    áĥķáĥĶáĥľ
    -0.07
     ÑĤÑĥда
    -0.07
    Ñĩке
    -0.06
    äºĨäºĭ
    -0.06
    羡
    -0.06
    ÃŃv
    -0.06
    ä»ĸ们已ç»ı
    -0.06
    POSITIVE LOGITS
    åIJĮä¸Ĭ
    0.09
    çļĦä¸Ģ款
    0.07
     ÙĥØ°ÙĦÙĥ
    0.07
    次äºİ
    0.06
    ès
    0.06
    dba
    0.06
    frm
    0.06
    -div
    0.06
    ama
    0.06
    onica
    0.06
    Activations Density 0.029%

    No Known Activations