© 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. 2929
    Prev
    Next
    INDEX
    Explanations

    say analog

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

    No Comments

    Negative Logits
     mutation
    -18.38
    permission
    -17.63
     mutate
    -17.50
    mut
    -17.50
    曲
    -17.38
     perm
    -17.25
    perms
    -17.13
    perm
    -16.88
     Permission
    -16.75
     mutations
    -16.63
    POSITIVE LOGITS
     analog
    69.50
    模拟
    60.75
     Analog
    60.50
     analogue
    57.25
     analogy
    48.25
     sim
    43.75
    (mock
    41.75
    sim
    40.00
     mock
    40.00
    (sim
    39.75
    Activations Density 0.088%

    No Known Activations