© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15365
    Prev
    Next
    INDEX
    Explanations

    say "capital letters"

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

    No Comments

    Negative Logits
    隍
    -19.00
    狐
    -18.63
    苫
    -17.25
    珐
    -17.25
    揪
    -17.25
    鹈
    -17.13
     Lac
    -17.00
    窖
    -16.50
    弋
    -16.50
    狐狸
    -16.25
    POSITIVE LOGITS
    (pm
    39.25
    (fm
    38.25
     PM
    36.75
    bm
    36.75
     BM
    36.50
    RAM
    36.25
    	pm
    36.25
    ram
    35.50
     xm
    35.50
    pm
    35.25
    Activations Density 6.697%

    No Known Activations