© 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. 17975
    Prev
    Next
    INDEX
    Explanations

    water in soil and reservoirs

    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
    çģ¼
    -0.08
    tros
    -0.08
     Elect
    -0.07
    inkt
    -0.07
     investe
    -0.07
    åħļæ´¾
    -0.07
    å±±æĿij
    -0.07
     heats
    -0.07
    åģľéĿł
    -0.06
    åħĥèĢģ
    -0.06
    POSITIVE LOGITS
     groundwater
    0.11
    åŃĶéļĻ
    0.10
     drainage
    0.10
    åľ°ä¸ĭæ°´
    0.10
    åľ°ä¸ĭ
    0.09
    壤
    0.09
    岩
    0.09
     soil
    0.09
    æ°´æĸĩ
    0.09
    éĢıæ°´
    0.09
    Activations Density 0.048%

    No Known Activations