© 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. 15004
    Prev
    Next
    INDEX
    Explanations

    titles

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

    No Comments

    Negative Logits
    abouts
    -16.25
    Lİ
    -16.13
     verg
    -16.00
    ��
    -15.81
    ardin
    -15.63
    ↵
    -15.63
    egra
    -15.56
     wr
    -15.56
    囹
    -15.44
    ooks
    -15.19
    POSITIVE LOGITS
    newsletter
    13.56
    握手
    13.06
     �
    12.94
    .hibernate
    12.81
    Sanders
    12.38
    .eclipse
    12.19
    _tls
    11.75
    .crypto
    11.69
     carpet
    11.63
    岳
    11.63
    Activations Density 1.835%

    No Known Activations