© 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. 1894
    Prev
    Next
    INDEX
    Explanations

    genetics

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

    No Comments

    Negative Logits
    elu
    -19.75
    CTS
    -19.50
     Shi
    -18.88
    orent
    -18.50
    CLU
    -18.50
    荥
    -17.50
    PIX
    -16.88
     Sham
    -16.88
    CLA
    -16.63
     BCE
    -16.63
    POSITIVE LOGITS
    对孩子
    14.06
    itten
    13.38
     lod
    13.25
    	union
    13.25
    我が
    13.19
     floor
    13.00
    .called
    12.88
    孩
    12.81
    男孩
    12.63
    叉
    12.50
    Activations Density 0.070%

    No Known Activations