© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61612
    Prev
    Next
    INDEX
    Explanations

    energy industry and related issues

    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
    ismus
    -0.07
    ç¡ħèĥ¶
    -0.07
    .Mutable
    -0.07
     FDA
    -0.07
    æ©¡çļ®
    -0.07
    ieden
    -0.07
    epage
    -0.06
     clinically
    -0.06
    éħ¸çĶľèĭ¦è¾£
    -0.06
     Ehren
    -0.06
    POSITIVE LOGITS
     energy
    0.14
    èĥ½æºIJ
    0.13
     electricity
    0.12
    energy
    0.11
     Energy
    0.11
    ãĤ¨ãĥįãĥ«ãĤ®ãĥ¼
    0.11
    Energy
    0.11
     power
    0.11
     kWh
    0.10
    çĶµåĬĽ
    0.10
    Activations Density 0.089%

    No Known Activations