© 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. 15178
    Prev
    Next
    INDEX
    Explanations

    N/A

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

    No Comments

    Negative Logits
    毛泽
    -17.63
    hone
    -17.50
     bright
    -16.38
     CActive
    -16.13
     Scri
    -15.75
    apon
    -15.75
    瘗
    -15.69
     ApiException
    -15.63
    溶解
    -15.44
     SMART
    -15.38
    POSITIVE LOGITS
     đông
    14.50
     enlisted
    14.06
     stir
    13.88
    ixo
    13.44
    霹
    12.69
     Sandwich
    12.63
    cox
    12.63
    dio
    12.56
     binder
    12.56
    serv
    12.56
    Activations Density 0.741%

    No Known Activations