© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3012
    Prev
    Next
    INDEX
    Explanations

    say ret

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

    No Comments

    Negative Logits
    镜
    -18.25
    mir
    -17.50
     mirrored
    -16.38
    mirror
    -15.88
    itic
    -15.50
     mirrors
    -15.44
    .Registry
    -15.19
     Registry
    -15.13
     analog
    -15.06
    _MODAL
    -15.06
    POSITIVE LOGITS
     ret
    55.25
    (ret
    48.75
    ret
    43.50
    	ret
    43.00
    .ret
    36.25
     Ret
    33.75
    $ret
    33.50
    _ret
    32.50
    Ret
    31.25
    -ret
    31.00
    Activations Density 0.014%

    No Known Activations