© 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. 21451
    Prev
    Next
    INDEX
    Explanations

    electromagnetic fields

    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
    LOSS
    -0.08
     sosi
    -0.08
    å°ºçłģ
    -0.08
    èĦļå°ĸ
    -0.07
    Asc
    -0.07
    skosten
    -0.07
    èĤ¾åĬŁèĥ½
    -0.07
    ãĥĭãĥ¼
    -0.07
    çĭ¬çĶŁåŃIJ女
    -0.07
    å¸Ĥæ°ijæĶ¿å±Ģ
    -0.07
    POSITIVE LOGITS
     electromagnetic
    0.11
    çĶµåľº
    0.10
    çĶµç£ģ
    0.10
     Field
    0.09
     electric
    0.09
     electro
    0.09
     electrom
    0.08
     electr
    0.08
    éĿĻçĶµ
    0.08
    -elect
    0.08
    Activations Density 0.003%

    No Known Activations