© 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. 15149
    Prev
    Next
    INDEX
    Explanations

    year numbers

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

    No Comments

    Negative Logits
    ��
    -21.00
    OPS
    -19.38
    ypy
    -19.13
    电子产品
    -19.13
    woke
    -18.88
    jec
    -18.13
    APO
    -17.75
    joy
    -17.38
    ượng
    -17.13
    orrent
    -17.00
    POSITIVE LOGITS
    isto
    12.31
     constr
    12.19
    Listener
    11.63
     Questions
    11.38
     Katz
    11.13
     now
    10.81
     mut
    10.75
     Lo
    10.75
     mutual
    10.69
    Al
    10.50
    Activations Density 0.019%

    No Known Activations