© 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. 2325
    Prev
    Next
    INDEX
    Explanations

    say cur

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

    No Comments

    Negative Logits
     forts
    -16.88
    clus
    -15.75
    械
    -14.81
    .atom
    -14.69
     ant
    -14.63
    (prop
    -14.44
    omid
    -14.38
    抗
    -14.31
    保罗
    -14.19
    =img
    -14.06
    POSITIVE LOGITS
     cur
    68.00
    (cur
    68.00
    cur
    67.00
    Cur
    66.50
    曲
    64.50
    [cur
    64.00
    	cur
    63.00
     curriculum
    60.00
    _cur
    60.00
     Cur
    60.00
    Activations Density 0.101%

    No Known Activations