© 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. 55928
    Prev
    Next
    INDEX
    Explanations

    punctuation following numbers

    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
    доб
    -0.07
    移
    -0.07
    perator
    -0.07
    Ø®ÙĪاÙĨ
    -0.07
     \''
    -0.07
    .Typed
    -0.07
    æ·ĭ
    -0.07
    ovable
    -0.07
    ç°ĩ
    -0.07
     Programmer
    -0.07
    POSITIVE LOGITS
    ä¸įèĭŁ
    0.08
    åī§
    0.07
    regel
    0.07
    uces
    0.07
    جا
    0.06
    linger
    0.06
    agra
    0.06
    æķ¢è¯´
    0.06
    飶åįİ
    0.06
    olos
    0.06
    Activations Density 0.066%

    No Known Activations