© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1776
    Prev
    Next
    INDEX
    Explanations

    say "mineral names"

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

    No Comments

    Negative Logits
    钙
    -63.50
     calcium
    -62.00
     Calcium
    -56.50
    Calc
    -50.75
     Ca
    -49.25
    calc
    -47.00
    Ca
    -46.75
     CALC
    -44.75
    CAL
    -44.25
    _cal
    -44.00
    POSITIVE LOGITS
    禾
    17.13
    丹麦
    15.31
     Ashe
    14.81
    朝鲜
    13.44
    狐
    13.13
    玩家
    12.88
    iat
    12.38
    agoon
    12.19
    蘑菇
    12.19
     Sport
    12.06
    Activations Density 0.057%

    No Known Activations