© 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. 57651
    Prev
    Next
    INDEX
    Explanations

    power and watts

    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
    ÄįÃŃ
    -0.08
    èĮ«èĮ«
    -0.08
    å¤ªè¿ľ
    -0.08
    -reset
    -0.07
     lengths
    -0.07
    -trigger
    -0.07
     Length
    -0.07
     parcours
    -0.07
    hlen
    -0.07
    ordo
    -0.07
    POSITIVE LOGITS
    åĬŁçİĩ
    0.14
     watts
    0.13
     watt
    0.12
    è¾ĵåĩºåĬŁçİĩ
    0.11
    æľĢ大åĬŁçİĩ
    0.11
    (power
    0.11
    åįĥçĵ¦
    0.10
     power
    0.10
    /power
    0.10
     dissip
    0.10
    Activations Density 0.029%

    No Known Activations