© 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. 17914
    Prev
    Next
    INDEX
    Explanations

    numbers in sequences

    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
    并ä¸įç®Ĺ
    -0.07
    razier
    -0.07
    pter
    -0.07
     Sousa
    -0.07
    lide
    -0.06
    纳德
    -0.06
    ìłĪ
    -0.06
    åĹ£
    -0.06
    iggers
    -0.06
    irl
    -0.06
    POSITIVE LOGITS
    第ä¸īæĿ¡
    0.08
    第ä¸ī
    0.08
    第ä¸īç§į
    0.08
     ÑĤÑĢеÑĤÑĮе
    0.08
    ä¸īæĺ¯
    0.08
    Serialization
    0.07
     III
    0.07
    第ä¸ī个
    0.07
    etc
    0.07
    ä¸īèĢħ
    0.07
    Activations Density 0.206%

    No Known Activations