© 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. 736
    Prev
    Next
    INDEX
    Explanations

    whole grains

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

    No Comments

    Negative Logits
    拉萨
    -20.13
     Troll
    -19.75
     mango
    -19.38
    榄
    -18.88
     minecraft
    -18.75
     MySql
    -18.63
     <?=
    -18.50
     userDao
    -18.38
     Joomla
    -17.88
     Maurit
    -17.88
    POSITIVE LOGITS
    adem
    14.69
    şe
    14.44
    olean
    14.00
    荩
    13.13
    ynet
    12.81
    项
    12.63
    逸
    12.44
    ofi
    12.38
     SH
    12.31
    eping
    12.31
    Activations Density 0.047%

    No Known Activations