© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14365
    Prev
    Next
    INDEX
    Explanations

    say "digits"

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

    No Comments

    Negative Logits
    bil
    -22.88
    拜师
    -19.38
    bor
    -19.00
    amination
    -18.50
    氨
    -18.50
    aida
    -18.25
    bir
    -18.13
    adem
    -17.75
     bitten
    -17.63
    bay
    -17.50
    POSITIVE LOGITS
    wo
    15.56
     violet
    15.00
    ewood
    13.56
    9
    13.44
    rite
    13.38
    1
    13.25
    7
    13.19
    cka
    13.19
    8
    13.13
     "-//
    13.13
    Activations Density 0.038%

    No Known Activations