© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1155
    Prev
    Next
    INDEX
    Explanations

    do not say cyber

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     cyber
    -24.75
     cybersecurity
    -22.63
     Cyber
    -22.13
     Axel
    -18.25
    网络安全
    -18.00
    axe
    -17.75
    ax
    -16.88
    metal
    -16.00
    黥
    -15.88
    �
    -15.50
    POSITIVE LOGITS
     token
    16.50
    ement
    16.38
    数据库
    16.25
    ouri
    16.25
    -token
    15.81
    雨
    15.63
    .getToken
    15.50
     tokens
    15.19
     rain
    15.06
    树木
    15.00
    Activations Density 0.255%

    No Known Activations