© 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. 14946
    Prev
    Next
    INDEX
    Explanations

    Native American references

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

    No Comments

    Negative Logits
    assel
    -18.88
    undi
    -18.00
     DRIVER
    -18.00
    ETS
    -17.25
    .Helper
    -16.25
    inki
    -16.25
    _pdf
    -16.00
    TPL
    -15.94
     CET
    -15.75
    CAPE
    -15.69
    POSITIVE LOGITS
    烂
    14.75
    /lab
    13.88
    bourne
    13.63
    辩证
    13.38
    jb
    13.31
     rot
    13.06
    arta
    13.06
     Yin
    13.00
    /sign
    12.94
    YZ
    12.94
    Activations Density 0.089%

    No Known Activations