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

    Neuronpedia

    Jacobian LensNEW
    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. 15289
    Prev
    Next
    INDEX
    Explanations

    say attack

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

    No Comments

    Negative Logits
     banking
    -18.88
     Banking
    -18.88
    钢管
    -18.75
    商业银行
    -18.63
    乡土
    -18.25
    ROAD
    -18.00
    银行
    -17.50
    铠
    -17.38
     Russia
    -17.25
     finance
    -17.25
    POSITIVE LOGITS
    attacks
    19.63
     attacks
    19.50
    trigger
    19.25
     attack
    19.00
     Attacks
    17.38
    攻击
    17.00
    attack
    17.00
     trigger
    16.88
     Attack
    16.00
     ATTACK
    15.94
    Activations Density 0.141%

    No Known Activations