© 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. 2416
    Prev
    Next
    INDEX
    Explanations

    say Mich

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

    No Comments

    Negative Logits
     leg
    -21.88
    Leg
    -21.50
    legen
    -20.25
    leg
    -18.38
     Leg
    -17.88
    lege
    -17.00
    _leg
    -16.63
     lég
    -16.38
    legt
    -16.38
    -leg
    -16.13
    POSITIVE LOGITS
    Mich
    56.50
     Mich
    56.25
    徐
    42.25
     Mic
    42.00
     Michel
    41.50
    Mic
    39.50
     mic
    38.25
     MIC
    36.00
     μ
    35.50
    mic
    33.00
    Activations Density 0.028%

    No Known Activations