© 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. 2902
    Prev
    Next
    INDEX
    Explanations

    say dist

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

    No Comments

    Negative Logits
    -ser
    -19.00
    帽
    -18.00
     Ser
    -18.00
    Ser
    -17.88
    eto
    -17.63
    �
    -17.13
     Dante
    -16.88
    _ser
    -16.75
    meric
    -16.50
     Jeremy
    -16.50
    POSITIVE LOGITS
     dist
    65.00
    dist
    55.75
    Dist
    52.50
    (dist
    50.75
     Dist
    50.00
    -dist
    48.25
    _dist
    47.75
    	dist
    47.25
    .dist
    44.00
    /dist
    42.50
    Activations Density 0.120%

    No Known Activations