© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 627
    Prev
    Next
    INDEX
    Explanations

    say "radio" words

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

    No Comments

    Negative Logits
     decks
    -19.38
    酒业
    -18.63
    花
    -18.38
    卡片
    -18.25
    酿酒
    -18.25
    花瓣
    -18.13
    椰
    -18.00
    南瓜
    -17.63
     deck
    -17.50
    雨
    -17.50
    POSITIVE LOGITS
     radio
    36.75
     radiation
    35.50
     Radio
    35.50
     Radiation
    34.25
    Radio
    34.00
    Radi
    33.50
    无线电
    32.75
    辐射
    32.00
    radi
    31.63
    radio
    31.38
    Activations Density 0.065%

    No Known Activations