© 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. 14480
    Prev
    Next
    INDEX
    Explanations

    Latin species names

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

    No Comments

    Negative Logits
    YC
    -18.50
     Lap
    -18.38
    YN
    -18.25
    萘
    -18.00
    NPC
    -17.75
    .recycle
    -17.75
    цикл
    -17.63
    Nic
    -17.13
    YP
    -17.13
    リング
    -16.88
    POSITIVE LOGITS
    -fw
    16.00
    ware
    15.31
    owl
    14.31
    aw
    14.31
    awa
    14.13
    嘉
    13.63
    ava
    13.56
    aire
    13.50
     Clare
    13.50
    傅
    13.44
    Activations Density 0.015%

    No Known Activations