© 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. 37926
    Prev
    Next
    INDEX
    Explanations

    electrostatic charge and layers

    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
    ä¸İæĸ¹æ³ķ
    -0.07
    baugh
    -0.07
    Å¡i
    -0.07
    rieg
    -0.07
     conting
    -0.07
     rif
    -0.07
    åįģåŃĹ
    -0.07
    å¾Ĵæīĭ
    -0.07
    ä¸İä¸ĸçķĮ
    -0.07
    Longitude
    -0.07
    POSITIVE LOGITS
    kul
    0.09
     charges
    0.08
     charge
    0.08
    charge
    0.08
     neutrality
    0.08
     salts
    0.08
    ä¸ŃåĴĮ
    0.08
     neutral
    0.08
    charges
    0.07
    èĸĦ
    0.07
    Activations Density 0.013%

    No Known Activations