© 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. 17672
    Prev
    Next
    INDEX
    Explanations

    instability and waves

    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
    笨
    -0.07
    Äĥr
    -0.07
     manh
    -0.07
    à¸ķัà¸Ļ
    -0.07
    çĴŁ
    -0.07
    æ¡£
    -0.07
    éĩijæŃ£
    -0.07
    æµĵæµĵ
    -0.07
    å±ħ士
    -0.07
    å½ĵäºĭ
    -0.06
    POSITIVE LOGITS
    waves
    0.10
     waves
    0.09
     instability
    0.09
     destabil
    0.09
    wave
    0.09
    çļĦä¼łæĴŃ
    0.09
     wave
    0.09
     propag
    0.08
     Waves
    0.08
    æ³¢
    0.08
    Activations Density 0.028%

    No Known Activations