© 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
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16372
    Prev
    Next
    INDEX
    Explanations

    classical citations

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

    No Comments

    Negative Logits
    pike
    -18.50
    rok
    -16.00
    克
    -15.81
    croft
    -15.56
    kart
    -15.25
    	cl
    -15.00
    uler
    -14.44
    cl
    -14.31
     Clair
    -14.19
    ulers
    -14.06
    POSITIVE LOGITS
    训
    17.13
    疳
    17.13
     Emerson
    17.00
    ysize
    16.63
    .vars
    16.63
    exo
    16.63
    注
    16.50
     LSU
    16.25
    ritz
    16.00
    咫
    15.94
    Activations Density 0.090%

    No Known Activations