© 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. 15996
    Prev
    Next
    INDEX
    Explanations

    ML terminology

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

    No Comments

    Negative Logits
     addAction
    -17.50
    uga
    -16.13
    专项行动
    -16.00
     Patt
    -15.94
    anka
    -15.69
     lashes
    -15.63
     Clan
    -15.56
    传闻
    -15.19
    <Action
    -15.13
     Buffy
    -15.00
    POSITIVE LOGITS
    ít
    15.88
    Prot
    14.25
    otr
    14.19
     prime
    14.19
    pector
    14.00
    射
    14.00
    _fire
    13.94
    .fm
    13.94
     evolved
    13.88
    胡
    13.75
    Activations Density 0.088%

    No Known Activations

    This feature has no known activations.