© 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. 26956
    Prev
    Next
    INDEX
    Explanations

    converges to, convergence results

    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
    UNS
    -0.07
    åŁ¹
    -0.07
    OLA
    -0.06
    à¸į
    -0.06
    æĮĸæİĺ
    -0.06
    åĨįæĿ¥
    -0.06
    以ä¸ĬçļĦ
    -0.06
    angk
    -0.06
    ä¸ĬæīĢ
    -0.06
     incom
    -0.06
    POSITIVE LOGITS
    _HAL
    0.08
    Replacement
    0.07
    è»Ł
    0.07
    软
    0.07
    å¿ĥæĥ³
    0.07
    .dc
    0.07
    æĥ¨éĩį
    0.07
    оÑģÑĤÑĢе
    0.07
    梯度
    0.07
    _weather
    0.07
    Activations Density 0.006%

    No Known Activations