© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39545
    Prev
    Next
    INDEX
    Explanations

    initiating phrases

    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
    å¯Ħ
    -0.08
     sedi
    -0.07
    æĺ¯å¥½
    -0.06
    æĺ¯åĶ¯ä¸Ģ
    -0.06
    vis
    -0.06
     tabindex
    -0.06
    æĪijå°±æĺ¯
    -0.06
     cuento
    -0.06
    cate
    -0.06
    ãģ£ãģ±ãĤĬ
    -0.06
    POSITIVE LOGITS
    holm
    0.09
    åħįåİ»
    0.09
    .stopPropagation
    0.08
    çŁĽçĽ¾çļĦ
    0.08
    è¦ģæ±Ĥåľ¨
    0.08
    кола
    0.08
    amat
    0.07
    .unlock
    0.07
    ç«ĭå¾·
    0.07
    ä¹ı
    0.07
    Activations Density 0.020%

    No Known Activations