© 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. 2262
    Prev
    Next
    INDEX
    Explanations

    say prime symbols

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

    No Comments

    Negative Logits
     ant
    -23.88
     Ant
    -22.00
    Ant
    -21.00
     Antar
    -20.50
     pos
    -20.13
    .pos
    -20.13
    	pos
    -19.00
    Dat
    -19.00
    (pos
    -18.88
    dat
    -18.75
    POSITIVE LOGITS
    ′
    45.25
     �
    43.75
    ″
    36.25
    ‒
    29.38
    †
    27.38
    ‡
    26.38
    ‵
    24.38
     src
    24.13
     btn
    23.75
    (src
    23.38
    Activations Density 0.036%

    No Known Activations