© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2470
    Prev
    Next
    INDEX
    Explanations

    modifier keys

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

    No Comments

    Negative Logits
    ippers
    -19.63
    -mouth
    -18.25
     CHIP
    -17.25
     wings
    -17.00
    Rpc
    -17.00
    넷
    -16.88
     MLP
    -16.88
    禺
    -16.75
     variance
    -16.50
    vic
    -16.50
    POSITIVE LOGITS
    交易
    14.50
    ড
    13.94
    раг
    13.63
    重庆
    13.13
    单价
    13.06
    浩
    12.88
    oodoo
    12.81
    乏
    12.50
    市场价格
    12.44
    可视
    12.38
    Activations Density 0.039%

    No Known Activations