© 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. 1720
    Prev
    Next
    INDEX
    Explanations

    Toxic

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

    No Comments

    Negative Logits
    动态
    -19.63
    alic
    -19.63
     dynamic
    -19.50
    etic
    -19.50
     mathematical
    -19.38
    Dynamic
    -18.50
    逻辑
    -18.25
    闳
    -18.13
     Mathematical
    -17.75
     Dynamic
    -17.13
    POSITIVE LOGITS
    machine
    16.50
     Sanford
    15.81
     machine
    15.75
    (machine
    15.63
    穆
    15.38
     Hund
    14.94
     Machines
    14.88
     machines
    14.38
    .machine
    14.38
     Machine
    14.31
    Activations Density 0.134%

    No Known Activations