© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17828
    Prev
    Next
    INDEX
    Explanations

    certain words followed by certain words

    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
    çīĽéĥİ
    -0.08
    ussi
    -0.07
    ä¼Ł
    -0.07
    ׾×ĺ
    -0.07
    orious
    -0.07
    æİı
    -0.07
    个好
    -0.07
    >>(
    -0.07
    anze
    -0.07
    æļ®
    -0.07
    POSITIVE LOGITS
    etc
    0.08
     etc
    0.07
    åĴĮéĩįçĤ¹
    0.07
    while
    0.07
     while
    0.07
    ritch
    0.07
    漸
    0.06
    eppe
    0.06
    *)&
    0.06
    soon
    0.06
    Activations Density 0.001%

    No Known Activations