© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1001
    Prev
    Next
    INDEX
    Explanations

    say double letters

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

    No Comments

    Negative Logits
    狮
    -15.88
    轩辕
    -15.06
    蜍
    -14.50
    неж
    -14.44
    苌
    -14.44
    mdb
    -14.31
    ergy
    -14.25
    邳
    -14.13
    DSA
    -14.00
    .hu
    -13.75
    POSITIVE LOGITS
     CC
    61.75
     SS
    58.25
     DD
    57.50
     cc
    56.75
     dd
    55.00
    (cc
    54.75
     BB
    52.75
    (CC
    52.75
     AA
    52.75
    	dd
    51.00
    Activations Density 0.999%

    No Known Activations