© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14534
    Prev
    Next
    INDEX
    Explanations

    code syntax

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

    No Comments

    Negative Logits
     Walton
    -17.50
     Pikachu
    -16.75
     pa
    -16.50
     poisoned
    -16.00
    -po
    -15.88
     advoc
    -15.75
    牢
    -15.75
    .pa
    -15.63
    _pa
    -15.50
    PubMed
    -15.50
    POSITIVE LOGITS
    願
    16.88
    ilan
    15.00
    K
    14.94
    ilingual
    14.88
    liga
    14.81
    不得转载
    14.69
     theory
    14.56
    流れ
    14.50
    iable
    14.25
    etch
    14.25
    Activations Density 0.689%

    No Known Activations