© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14835
    Prev
    Next
    INDEX
    Explanations

    say "format specifiers"

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

    No Comments

    Negative Logits
     Infinite
    -17.00
     Sheridan
    -16.38
     Dexter
    -15.44
    ✎
    -14.81
    abol
    -14.25
    aceous
    -14.19
     Confeder
    -14.13
    湘西
    -14.06
    Canadian
    -13.75
    odom
    -13.50
    POSITIVE LOGITS
    %%%%
    17.00
    /%
    16.75
     \"%
    16.38
    %%
    15.81
    ">%
    15.63
    %n
    15.38
    kus
    15.25
     "[%
    15.13
    :%
    14.94
    %d
    14.81
    Activations Density 0.015%

    No Known Activations