© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14788
    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
    ADE
    -18.00
    ADR
    -16.38
    śli
    -15.94
     desn
    -15.94
    ropri
    -15.88
    isse
    -15.75
    ADO
    -15.63
    isten
    -15.63
    рен
    -15.38
    zers
    -15.25
    POSITIVE LOGITS
     Yuk
    15.31
    个百分点
    14.44
    ysz
    14.06
    uml
    14.06
     Participant
    13.94
     shoulders
    13.63
     Oct
    13.63
    ov
    13.38
     outside
    13.25
    _heads
    13.25
    Activations Density 0.008%

    No Known Activations