© 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. 15290
    Prev
    Next
    INDEX
    Explanations

    author A initial

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

    No Comments

    Negative Logits
    RB
    -20.63
    RAP
    -19.13
    ران
    -19.00
    RD
    -18.75
     r
    -18.63
    MI
    -18.38
     RCC
    -18.25
    RL
    -18.00
    RIES
    -17.75
    >r
    -17.75
    POSITIVE LOGITS
    蔚
    17.00
     attic
    16.50
    aiser
    16.13
     weer
    16.13
     piece
    15.38
     Antoine
    15.38
     anthem
    15.06
     anecd
    15.00
    畴
    14.50
    鲵
    14.31
    Activations Density 0.008%

    No Known Activations