© 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. 14812
    Prev
    Next
    INDEX
    Explanations

    say numbers

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

    No Comments

    Negative Logits
     метро
    -19.75
    ADO
    -19.75
    abet
    -19.50
    AFX
    -19.25
    ibel
    -18.75
    adata
    -18.63
    aData
    -18.38
     Abed
    -18.38
    adia
    -18.38
    icky
    -18.38
    POSITIVE LOGITS
    摸
    12.69
     bo
    12.44
    om
    12.38
    ɾ
    12.19
    OfClass
    12.19
    olum
    12.13
    o
    12.13
     gro
    11.94
     nog
    11.94
    nock
    11.75
    Activations Density 0.017%

    No Known Activations