© 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. 8946
    Prev
    Next
    INDEX
    Explanations

    bubble or bubbles

    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
    acey
    -0.08
    å·´åĭĴ
    -0.08
    OfMonth
    -0.08
    ä¸įæ¸Ŀ
    -0.08
    ä¸į移
    -0.07
    ahl
    -0.07
    iced
    -0.07
    ä¸įæĺİçļĦ
    -0.07
    edor
    -0.07
    림
    -0.07
    POSITIVE LOGITS
     bubbles
    0.11
    æ°Ķ泡
    0.11
     bubble
    0.09
    çł´çģŃ
    0.09
    bubble
    0.09
    gai
    0.08
    arella
    0.08
    terie
    0.08
    stick
    0.08
    çł´è£Ĥ
    0.08
    Activations Density 0.044%

    No Known Activations