© 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. 2869
    Prev
    Next
    INDEX
    Explanations

    say "μ"

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

    No Comments

    Negative Logits
     prop
    -21.50
    NewProp
    -20.50
    [prop
    -20.38
    prop
    -20.13
    -prop
    -19.88
    [obj
    -19.50
    	prop
    -18.50
    PROP
    -18.13
     Prop
    -18.00
    (prop
    -17.75
    POSITIVE LOGITS
     μ
    44.50
    μ
    40.75
    徐
    37.25
     Mic
    32.25
     mic
    30.38
    Mic
    29.63
     MUT
    29.13
     mu
    28.38
     ut
    28.00
    (mut
    27.00
    Activations Density 0.024%

    No Known Activations