© 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. 60266
    Prev
    Next
    INDEX
    Explanations

    braking systems and related components

    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
     Nest
    -0.07
     миÑĢо
    -0.07
    nest
    -0.07
    å·¢
    -0.07
     nest
    -0.07
    çIJ¢
    -0.07
    åѵ
    -0.06
    æµģåĬ¨çļĦ
    -0.06
    æıĴ座
    -0.06
    交çĶµ
    -0.06
    POSITIVE LOGITS
     brake
    0.11
     braking
    0.11
     brakes
    0.10
    åĪ¹è½¦
    0.09
     Brake
    0.09
    åĪ¶åĬ¨
    0.09
     phanh
    0.09
    æĢ§èĥ½
    0.09
    åĪ¹
    0.08
     ÑĤоÑĢм
    0.08
    Activations Density 0.029%

    No Known Activations