© 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. 2102
    Prev
    Next
    INDEX
    Explanations

    retrieve

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

    No Comments

    Negative Logits
    Fac
    -24.25
     ep
    -23.13
    fac
    -23.00
    Ep
    -21.25
     Ep
    -20.75
    _ep
    -18.75
     Fac
    -17.75
    (ep
    -17.25
    argin
    -16.88
    植
    -16.63
    POSITIVE LOGITS
    Ret
    46.00
     retrie
    44.75
     retrieval
    44.50
     retrieved
    44.50
     Retrie
    43.50
    Retrieve
    42.50
     retrieve
    41.25
     RET
    41.25
     Ret
    41.00
    .Ret
    41.00
    Activations Density 0.136%

    No Known Activations