© 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. 24841
    Prev
    Next
    INDEX
    Explanations

    physics and engineering concepts

    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
    desk
    -0.07
    åĪ°å°¾
    -0.07
    èĢĻ
    -0.07
    ëĮĢë¡ľ
    -0.07
    äºĨçļĦ
    -0.07
    oto
    -0.07
    ãģ¾ãģ¾
    -0.07
    lant
    -0.07
    viders
    -0.07
    habi
    -0.07
    POSITIVE LOGITS
     whose
    0.11
    -like
    0.10
    whose
    0.10
     model
    0.09
     theory
    0.09
     undergoing
    0.08
     equation
    0.08
     cuyo
    0.08
    çī¹æľīçļĦ
    0.08
     cuya
    0.07
    Activations Density 0.027%

    No Known Activations