© 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. 1863
    Prev
    Next
    INDEX
    Explanations

    php code include

    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
    agi
    -0.07
    hle
    -0.07
    asz
    -0.07
    ueux
    -0.07
     غÙĬرÙĩا
    -0.07
    为己
    -0.07
    etz
    -0.07
    eteg
    -0.07
    导åĩºæķ°æį®
    -0.07
    기ëıĦ
    -0.07
    POSITIVE LOGITS
     //(
    0.08
     either
    0.07
    è¦ģä¹Īæĺ¯
    0.07
    æł¹æį®ä½łçļĦ
    0.07
    åĭ¤
    0.07
    æł¹æį®ä¸ªäºº
    0.07
    esto
    0.06
     Ø¥Ùħا
    0.06
    instanc
    0.06
    æł¹æį®åħ¶
    0.06
    Activations Density 0.057%

    No Known Activations