© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15010
    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
    CSR
    -21.25
    EOS
    -19.88
    ERIC
    -19.88
    ecs
    -19.75
    ATAR
    -19.63
    (ec
    -19.38
    BOR
    -19.13
    IPH
    -19.13
    爱尔
    -19.00
    Sher
    -18.88
    POSITIVE LOGITS
     plateau
    15.75
    叠加
    14.31
    <<<<<<<
    14.13
     проб
    14.00
    海
    13.94
     �
    13.69
    首席
    13.69
    板
    13.63
    宫廷
    13.19
    /stdc
    12.94
    Activations Density 0.026%

    No Known Activations