© 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. 15404
    Prev
    Next
    INDEX
    Explanations

    C type declarations

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

    No Comments

    Negative Logits
    �
    -17.38
     
    -15.94
    …↵↵
    -15.69
    …↵
    -14.69
    …"
    -14.63
     spirit
    -14.25
    "
    -14.19
     […
    -14.06
     […]↵↵
    -14.06
    .wordpress
    -13.94
    POSITIVE LOGITS
    edata
    20.00
     inputData
    19.00
    ldata
    18.63
    vsp
    18.50
    umd
    18.38
     Stats
    18.25
    TPL
    18.13
    msgid
    18.00
     outputPath
    17.88
    ksz
    17.88
    Activations Density 0.275%

    No Known Activations