© 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. 14605
    Prev
    Next
    INDEX
    Explanations

    newline

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

    No Comments

    Negative Logits
     Kirby
    -19.88
    jer
    -19.88
    tower
    -19.75
    tam
    -19.75
    ammer
    -19.75
    阶梯
    -19.13
    cir
    -18.88
    滔
    -18.88
    esser
    -18.88
    immer
    -18.88
    POSITIVE LOGITS
    aland
    21.00
     sidewalk
    19.25
    ardi
    19.00
    片区
    18.63
     pedals
    18.63
    nid
    18.50
     nid
    18.50
    _PED
    18.38
     palate
    17.75
    fds
    17.50
    Activations Density 0.843%

    No Known Activations