© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2223
    Prev
    Next
    INDEX
    Explanations

    heavenly stems

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

    No Comments

    Negative Logits
    .den
    -17.25
    ems
    -15.75
    den
    -15.25
    _SEG
    -14.75
    _den
    -14.44
    구
    -14.25
    EMS
    -14.19
    rove
    -14.19
     erv
    -14.19
     Med
    -14.06
    POSITIVE LOGITS
    丙
    69.00
    乙
    69.00
    戊
    60.75
    甲
    57.75
    壬
    53.25
    庚
    51.00
    癸
    50.25
    eth
    48.25
     meth
    47.25
     Eth
    46.75
    Activations Density 0.042%

    No Known Activations