© 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. 2123
    Prev
    Next
    INDEX
    Explanations

    say prefixes

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

    No Comments

    Negative Logits
    =res
    -20.13
    [res
    -18.25
    oves
    -15.63
    Mut
    -15.25
    ＇
    -14.94
    Mic
    -14.88
     Mur
    -14.69
    Mult
    -14.56
     Mult
    -14.50
     Dat
    -14.44
    POSITIVE LOGITS
     geo
    33.75
     Geo
    32.00
     nano
    30.50
    Geo
    30.00
     mini
    29.75
    demo
    28.88
     thermo
    28.75
     demo
    28.50
     multi
    28.25
    (meta
    28.00
    Activations Density 0.251%

    No Known Activations