© 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. 2142
    Prev
    Next
    INDEX
    Explanations

    say spec

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

    No Comments

    Negative Logits
    erman
    -18.00
    emy
    -16.13
     Er
    -15.50
    .cur
    -14.81
    dem
    -14.56
    .span
    -14.38
     arr
    -14.19
    arr
    -13.69
    Er
    -13.63
    旬
    -13.38
    POSITIVE LOGITS
     spec
    80.50
    spec
    78.00
     Spec
    76.50
    Spec
    74.00
    	spec
    70.50
    (spec
    69.50
    _spec
    67.50
    .spec
    65.50
     specs
    64.00
     specification
    62.75
    Activations Density 0.272%

    No Known Activations