© 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. 14351
    Prev
    Next
    INDEX
    Explanations

    say ends with O

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

    No Comments

    Negative Logits
    roe
    -26.75
    ROTO
    -25.00
    oose
    -25.00
    loe
    -24.75
    oron
    -24.63
    oro
    -24.38
    orro
    -24.00
    bö
    -23.50
     Mojo
    -23.50
    rosso
    -23.25
    POSITIVE LOGITS
    盯
    15.44
    鲭
    14.75
    emet
    14.19
     Ramp
    14.06
    万亩
    13.88
     anmeld
    13.75
    embr
    13.50
    ame
    13.44
    剃
    13.44
    詹姆斯
    13.38
    Activations Density 1.200%

    No Known Activations