© 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. 2962
    Prev
    Next
    INDEX
    Explanations

    say rep

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

    No Comments

    Negative Logits
     ret
    -21.38
    ret
    -20.38
     seg
    -19.63
     mor
    -19.13
     moral
    -18.75
    (ret
    -18.13
    	ret
    -18.13
    pres
    -18.00
     Moral
    -17.75
    道德
    -16.88
    POSITIVE LOGITS
     replic
    41.75
     replication
    40.75
     replicate
    40.50
     replicated
    38.25
     replica
    36.75
     replicas
    35.00
     Replica
    33.75
    Rep
    31.25
    (rep
    29.75
    rep
    28.63
    Activations Density 0.074%

    No Known Activations