© 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. 2664
    Prev
    Next
    INDEX
    Explanations

    say cont

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

    No Comments

    Negative Logits
    _serial
    -20.25
    (serial
    -19.25
    .serializer
    -18.75
    甲
    -18.75
     serial
    -18.50
    utch
    -18.50
    serial
    -18.25
     Serial
    -17.63
     mutation
    -17.63
     meth
    -17.25
    POSITIVE LOGITS
     cont
    36.75
    Cont
    35.00
    cont
    34.25
    	cont
    33.75
     Cont
    33.25
    -cont
    29.13
    (cont
    28.38
     ctx
    26.88
    顾
    26.13
    .cont
    25.75
    Activations Density 0.107%

    No Known Activations