© 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. 17157
    Prev
    Next
    INDEX
    Explanations

    recursive links; recurrence relation; recursive approach; links; Editor's

    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
    æĺ¥å¤ıç§ĭåĨ¬
    -0.07
    ÙĪرÙĩ
    -0.07
    éĹĨ
    -0.07
    aise
    -0.07
     Haust
    -0.07
    andom
    -0.07
    .match
    -0.07
    gan
    -0.07
    æĺ¯ä¸Ģ段
    -0.06
    濯
    -0.06
    POSITIVE LOGITS
    .unlink
    0.07
    导
    0.07
    åĵģ
    0.07
    रण
    0.07
    å¨ĩ
    0.07
    akh
    0.07
    è¾Ī
    0.07
    éĵ¾
    0.07
    NEXT
    0.07
    åĭĴ
    0.07
    Activations Density 0.001%

    No Known Activations