© 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. 2683
    Prev
    Next
    INDEX
    Explanations

    proposition

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

    No Comments

    Negative Logits
     regs
    -21.75
     sim
    -19.63
     dir
    -19.38
    有机
    -18.88
    基
    -18.88
    pNet
    -18.75
     Decomp
    -18.50
    util
    -18.38
     util
    -18.25
     vec
    -18.13
    POSITIVE LOGITS
     proposition
    41.50
     Proposition
    37.50
     propositions
    36.00
    _prop
    22.25
    Prop
    22.13
     propos
    21.13
     props
    19.63
    提案
    19.13
    =pos
    18.38
    [pos
    18.13
    Activations Density 0.069%

    No Known Activations