© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3074
    Prev
    Next
    INDEX
    Explanations

    say reasoning

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

    No Comments

    Negative Logits
     bond
    -16.38
    bond
    -16.38
    lemen
    -16.13
     deco
    -16.00
     bois
    -15.50
     project
    -15.31
    棹
    -14.88
    鹍
    -14.44
    deer
    -14.25
    EDA
    -14.19
    POSITIVE LOGITS
    AGENT
    15.06
    hip
    15.06
    锁
    14.56
    locks
    14.25
    (agent
    14.00
    locked
    13.88
    一线城市
    13.75
    ampp
    13.56
    agents
    13.50
    anges
    13.31
    Activations Density 0.025%

    No Known Activations