© 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. 63114
    Prev
    Next
    INDEX
    Explanations

    tension, strain, stress, length

    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
    女巫
    -0.08
     ÑĦе
    -0.08
    æĹĭé£İ
    -0.08
    èģļç±»
    -0.08
     sweeping
    -0.08
    åĪ©æµ¦
    -0.07
    æ³¼
    -0.07
    émon
    -0.07
     sweep
    -0.07
    _cluster
    -0.07
    POSITIVE LOGITS
     tension
    0.10
    伸éķ¿
    0.10
     strain
    0.10
    æĭī伸
    0.09
    æĿIJ
    0.09
     stress
    0.09
    æĿIJæĸĻçļĦ
    0.08
     transmitting
    0.08
    æī¿åıĹ
    0.08
    åºĶåĬĽ
    0.08
    Activations Density 0.005%

    No Known Activations