© 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. 2547
    Prev
    Next
    INDEX
    Explanations

    say par

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

    No Comments

    Negative Logits
    乙
    -24.25
     mut
    -21.38
     vec
    -20.63
     doc
    -20.50
    vec
    -20.25
     docs
    -19.63
     temp
    -18.50
    (vec
    -18.25
    =tmp
    -18.25
    ,tmp
    -18.13
    POSITIVE LOGITS
     paradigm
    31.13
     Parad
    30.38
     parad
    29.38
     Par
    26.50
    Par
    26.50
    par
    23.88
     par
    23.88
     Param
    23.50
    (par
    23.50
    -par
    23.00
    Activations Density 0.045%

    No Known Activations