© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15169
    Prev
    Next
    INDEX
    Explanations

    say 0

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

    No Comments

    Negative Logits
     Olive
    -20.50
    鞠
    -20.25
    .esp
    -19.75
    莲花
    -19.50
    槲
    -19.38
    уль
    -19.25
     dome
    -19.13
    oleon
    -18.88
    lein
    -18.88
    oose
    -18.75
    POSITIVE LOGITS
    ritz
    15.94
    toy
    15.81
     Cory
    15.63
    �
    14.94
    trl
    14.50
    4
    14.44
     rex
    14.13
    rots
    14.06
    STRACT
    13.81
     Bryant
    13.50
    Activations Density 0.056%

    No Known Activations