© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1347
    Prev
    Next
    INDEX
    Explanations

    particle physics

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

    No Comments

    Negative Logits
     Miner
    -19.63
     pumping
    -19.63
    COPE
    -19.50
    水务
    -19.25
    Brain
    -19.00
     brain
    -18.50
     Cooke
    -17.75
     swell
    -17.63
    脑
    -17.50
    社会化
    -17.38
    POSITIVE LOGITS
    �
    13.25
    :animated
    12.75
     army
    12.31
    python
    12.06
    enuine
    12.00
    为客户
    11.81
    誓
    11.63
     Egyptian
    11.63
    衣
    11.63
    (serial
    11.56
    Activations Density 0.087%

    No Known Activations