© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15537
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     landslide
    -19.63
    	cl
    -19.50
    slide
    -19.00
     Linden
    -18.88
    (cl
    -18.88
    _cl
    -18.88
     cl
    -18.88
     slag
    -18.75
     Cl
    -18.50
     kl
    -18.50
    POSITIVE LOGITS
     Easter
    20.88
     Reco
    20.75
    expo
    20.13
    reo
    19.38
    襄阳
    19.13
     quint
    18.75
    stro
    18.75
     NEO
    18.50
     Angelo
    18.50
    antar
    18.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.