© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16301
    Prev
    Next
    INDEX
    Explanations

    say "charge" words

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trúc
    -17.88
     Wend
    -16.13
    =sc
    -15.56
     scape
    -15.25
    .fixture
    -15.25
     Marcel
    -15.25
    -transparent
    -15.19
     création
    -15.13
    _MT
    -15.13
     trem
    -15.13
    POSITIVE LOGITS
    充电
    38.50
     charge
    36.75
     charging
    36.00
     charg
    34.50
    charge
    34.50
     charged
    34.00
     charges
    33.50
     charger
    33.00
     Charge
    32.75
    charg
    32.50
    Activations Density 0.130%

    No Known Activations