© 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. 15271
    Prev
    Next
    INDEX
    Explanations

    [month] => [day]

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

    No Comments

    Negative Logits
    ogens
    -19.75
    Torrent
    -19.38
    enis
    -18.88
    clinic
    -18.38
    nier
    -18.25
    hound
    -18.25
    anio
    -18.25
    HEST
    -18.13
    enet
    -18.13
    oxide
    -18.13
    POSITIVE LOGITS
     inde
    12.69
     ph
    11.81
    1
    11.13
     ap
    11.00
     u
    11.00
    apt
    10.63
    IL
    10.44
     Ph
    10.38
     pred
    10.38
    ÿ
    10.31
    Activations Density 0.022%

    No Known Activations