© 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. 56914
    Prev
    Next
    INDEX
    Explanations

    zero digits, null, or zeros

    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
    ocard
    -0.08
    æ¯ıåIJį
    -0.07
    verband
    -0.07
    strup
    -0.07
    íķĢ
    -0.07
     xô
    -0.07
     htmlentities
    -0.07
    venge
    -0.07
    ãģľãĤĵ
    -0.07
    رÙĪض
    -0.07
    POSITIVE LOGITS
    æĪĸæľª
    0.08
    èĴľ
    0.08
     zeros
    0.07
    /null
    0.07
    åĬ©
    0.07
     kosong
    0.07
    ä¸ºéĽ¶
    0.07
    空
    0.07
    qu
    0.07
    æĪĸä¸į
    0.07
    Activations Density 0.017%

    No Known Activations