© 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. 2629
    Prev
    Next
    INDEX
    Explanations

    say arr

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

    No Comments

    Negative Logits
    capital
    -17.38
     Capital
    -17.38
    .Cap
    -16.88
    甸
    -16.88
     pets
    -16.63
    Cons
    -16.50
    .cap
    -16.38
     pet
    -16.25
     capital
    -16.13
    宗
    -15.88
    POSITIVE LOGITS
     arr
    68.00
     arrangement
    66.50
    arr
    66.50
     Arr
    65.50
    [arr
    63.00
     arrangements
    62.25
    	arr
    61.00
    Arr
    60.75
    ,arr
    58.25
    (arr
    56.25
    Activations Density 0.245%

    No Known Activations