© 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. 2419
    Prev
    Next
    INDEX
    Explanations

    say consensus

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

    No Comments

    Negative Logits
    =obj
    -21.13
    (obj
    -20.63
     obj
    -19.13
     val
    -18.75
    义
    -18.63
     tube
    -18.50
    義
    -18.25
    	obj
    -18.00
    (val
    -17.88
    )obj
    -17.88
    POSITIVE LOGITS
     consensus
    18.38
    共识
    17.63
     equilibrium
    17.13
    uai
    16.63
    iaux
    16.38
    Pol
    15.94
    emer
    15.63
    許
    15.19
     Resolver
    15.00
    perm
    14.94
    Activations Density 0.101%

    No Known Activations