© 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. 2104
    Prev
    Next
    INDEX
    Explanations

    say recall

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

    No Comments

    Negative Logits
    =res
    -24.63
     det
    -23.00
    (res
    -21.75
    师
    -21.38
    -det
    -21.25
    [res
    -21.25
    res
    -20.25
     merit
    -20.13
    mer
    -19.88
     mer
    -19.88
    POSITIVE LOGITS
    recall
    35.25
     recall
    33.00
    _recall
    31.50
     recalls
    29.88
     Recall
    29.63
     recalled
    28.38
     recalling
    24.25
    召回
    22.13
     Relay
    20.88
     rel
    19.00
    Activations Density 0.102%

    No Known Activations