© 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. 49467
    Prev
    Next
    INDEX
    Explanations

    words 'A' to

    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
    çīĪ车åŀĭ
    -0.08
    ä¸Ģè¯į
    -0.08
    aded
    -0.08
    ahari
    -0.07
    ä¸Ģ女
    -0.07
    è¿Ļ个è¯į
    -0.07
    æĸ¹éĿ¢ä¹Ł
    -0.07
     bulundu
    -0.07
    å¸Ĥæĸ°
    -0.07
     (!((
    -0.07
    POSITIVE LOGITS
    oces
    0.07
    ographique
    0.07
     olev
    0.06
    avanaugh
    0.06
    atif
    0.06
    uiltin
    0.06
    oo
    0.06
    ologique
    0.06
    autaire
    0.06
    ulaire
    0.06
    Activations Density 0.658%

    No Known Activations