© 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. 15054
    Prev
    Next
    INDEX
    Explanations

    say 0

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

    No Comments

    Negative Logits
     Zucker
    -20.00
    Bond
    -19.50
     Manor
    -18.75
     Bond
    -18.75
    BOR
    -18.50
    anken
    -18.50
    adel
    -18.38
     TOM
    -18.13
    achi
    -17.88
     Cheney
    -17.88
    POSITIVE LOGITS
     scalp
    14.88
    荸
    14.56
    ern
    14.56
    莼
    14.44
    brush
    14.19
    scri
    13.88
    empt
    13.81
     assim
    13.63
    陲
    13.50
    �
    13.31
    Activations Density 0.049%

    No Known Activations