© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 230
    Prev
    Next
    INDEX
    Explanations

    say sequencing terms

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

    No Comments

    Negative Logits
    VB
    -18.75
     Tick
    -18.13
     Mell
    -17.75
    ouns
    -17.63
    andler
    -17.50
    甜
    -17.38
     tick
    -16.88
     cheeks
    -16.88
    Tick
    -16.75
     ticks
    -16.75
    POSITIVE LOGITS
    reads
    16.75
    strand
    16.63
     threads
    16.50
     stranded
    16.25
     sam
    16.25
     seq
    16.13
     SAM
    16.13
     Illum
    16.00
     strand
    15.94
     Strand
    15.88
    Activations Density 0.067%

    No Known Activations