© 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. 26454
    Prev
    Next
    INDEX
    Explanations

    magnetic field conditions

    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
    äºİäºĭ
    -0.08
     мÑĥÑģоÑĢ
    -0.07
    teria
    -0.07
    ptime
    -0.07
    ereien
    -0.07
     Muhamm
    -0.07
     milik
    -0.07
    åĩºèº«çļĦ
    -0.07
     pneumat
    -0.07
    å°ıéĿĴ
    -0.07
    POSITIVE LOGITS
    æĸ¹åIJij
    0.09
     regime
    0.08
    å¾ģ
    0.08
    richtung
    0.08
     direction
    0.07
    argent
    0.07
    çļĦæĸ¹åIJij
    0.07
    ä¸ĭå®ļ
    0.07
    浦
    0.07
    åħĨ
    0.07
    Activations Density 0.017%

    No Known Activations