© 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. 39070
    Prev
    Next
    INDEX
    Explanations

    then followed by a word

    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
    .part
    -0.07
    наÑĩале
    -0.07
    è¿Ħä»Ĭ为æŃ¢
    -0.06
     comport
    -0.06
    اÙĨÙĪ
    -0.06
    ç¬ijå¾Ĺ
    -0.06
    æĹłä¸Ĭ
    -0.06
    èĢĮæѤæŶ
    -0.06
     harb
    -0.06
     pot
    -0.06
    POSITIVE LOGITS
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    0.11
     afterward
    0.11
     subsequent
    0.09
    lyn
    0.09
     afterwards
    0.09
     subsequently
    0.09
    æİ¥çĿĢ
    0.09
     ensuite
    0.09
    åĨįåĬłä¸Ĭ
    0.08
    ÙģÙĪر
    0.08
    Activations Density 0.083%

    No Known Activations