© 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. 45942
    Prev
    Next
    INDEX
    Explanations

    automotive and aerospace industries

    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
    ç«ł
    -0.07
    -ish
    -0.07
    -topic
    -0.07
    ä¸įçIJĨ
    -0.07
    bie
    -0.07
     arrangement
    -0.06
    ä¸įèĩª
    -0.06
     remembering
    -0.06
    æľ¬
    -0.06
    åĥµ
    -0.06
    POSITIVE LOGITS
    ä¸ŃçļĦåºĶçĶ¨
    0.09
    èĭĽåĪ»
    0.08
    æĬĢæľ¯è¦ģæ±Ĥ
    0.08
    ä»ķæ§ĺ
    0.08
    ä»ĸ们éľĢè¦ģ
    0.08
     applications
    0.08
     clients
    0.08
    ãģ§ä½¿çĶ¨
    0.08
     exige
    0.08
     demanding
    0.08
    Activations Density 0.791%

    No Known Activations