© 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. 45464
    Prev
    Next
    INDEX
    Explanations

    `Services` or `.class` and math notation

    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
     Chinh
    -0.08
    .rf
    -0.08
     ЧеÑĢно
    -0.07
    ÑıÑģÑĮ
    -0.07
    .sample
    -0.07
    ÙĪز
    -0.07
    çĴ¨
    -0.07
     Auff
    -0.07
    å½±è¯Ħ
    -0.07
     Finger
    -0.07
    POSITIVE LOGITS
    åį³
    0.08
    éĤ£å°±æĺ¯
    0.08
    æ²ģ
    0.07
    åį³ä»¥
    0.07
    анÑĤи
    0.07
    çŁ¥åħ¶
    0.07
    arana
    0.07
    Ñĥд
    0.07
    angu
    0.07
    éļħ
    0.06
    Activations Density 0.002%

    No Known Activations