© 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. 38182
    Prev
    Next
    INDEX
    Explanations

    power

    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
    ä¸ĩåį·
    -0.08
    rug
    -0.08
    å¾®è§Ĥ
    -0.07
    ç³Ļ
    -0.07
    é²
    -0.07
    èIJ½èĬ±
    -0.07
    ãĥŀãĤ·ãĥ³
    -0.07
    模æĿ¿
    -0.07
    uken
    -0.07
    éķľ
    -0.07
    POSITIVE LOGITS
     powering
    0.16
     power
    0.13
     recharge
    0.12
    -powered
    0.12
     powered
    0.12
    powered
    0.12
    åĬŁçİĩ
    0.11
    çĶµæºIJ
    0.11
     electricity
    0.11
    /power
    0.11
    Activations Density 0.205%

    No Known Activations