© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 1812
    Prev
    Next
    INDEX
    Explanations

    signal processing and detection

    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
    好äºĭ
    -0.06
    akest
    -0.06
    éĻIJåĪ¶çļĦ
    -0.06
    éĻIJåĪ¶æĢ§
    -0.06
    æݧèĤ¡æľīéĻIJåħ¬åı¸
    -0.06
    æľªçĦ¶
    -0.06
    ç½¹
    -0.06
    åij¨è½¬
    -0.06
    æĩ¸
    -0.06
    èĶĵ延
    -0.06
    POSITIVE LOGITS
    滤波åĻ¨
    0.10
     processing
    0.09
     waveform
    0.09
    滤波
    0.09
    -processing
    0.09
    (signal
    0.08
    æİ¥æĶ¶
    0.08
     modulation
    0.08
     Detection
    0.08
    processing
    0.08
    Activations Density 0.065%

    No Known Activations