© 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. 2602
    Prev
    Next
    INDEX
    Explanations

    say "Mu" words

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

    No Comments

    Negative Logits
     val
    -19.88
    	val
    -18.75
     iter
    -17.88
    =val
    -17.88
    [val
    -17.75
    (val
    -17.75
    val
    -17.63
    ,val
    -17.38
     lib
    -17.00
    etro
    -17.00
    POSITIVE LOGITS
     Muhammad
    35.50
    Mu
    33.50
    徐
    33.25
     MUT
    31.88
     μ
    29.25
    (mut
    28.25
    mut
    28.00
     Mut
    27.75
    Mut
    27.50
    _mut
    27.25
    Activations Density 0.036%

    No Known Activations