© 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. 2554
    Prev
    Next
    INDEX
    Explanations

    phenomenon

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

    No Comments

    Negative Logits
    cert
    -21.25
     cert
    -19.88
     Cert
    -19.50
    套
    -19.50
     recursion
    -19.25
     certs
    -19.25
    -rec
    -19.13
    (rec
    -18.88
     recurs
    -18.75
    Certificate
    -18.63
    POSITIVE LOGITS
    现象
    60.50
     Phen
    54.25
    phen
    49.25
     phen
    49.25
     phenomenon
    48.75
    的现象
    46.25
     phenomena
    43.75
     fen
    37.75
     phenotype
    35.50
     Fen
    32.25
    Activations Density 0.110%

    No Known Activations