© 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. 2175
    Prev
    Next
    INDEX
    Explanations

    say 互

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

    No Comments

    Negative Logits
    _penalty
    -18.75
     Prescott
    -17.38
     precip
    -15.44
    pen
    -15.19
     Penalty
    -15.13
     Hubbard
    -14.69
    allery
    -14.69
    val
    -14.63
     regenerate
    -14.63
    PLIT
    -14.56
    POSITIVE LOGITS
    互
    77.00
     mut
    75.50
    mut
    73.00
    Mut
    73.00
     Mut
    71.50
    (mut
    70.50
     mutual
    59.25
    _mut
    58.50
     MUT
    54.75
     mutant
    53.25
    Activations Density 0.050%

    No Known Activations