© 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. 14565
    Prev
    Next
    INDEX
    Explanations

    say font names

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

    No Comments

    Negative Logits
     Kills
    -18.13
    ót
    -18.00
     чел
    -16.25
    ucks
    -16.00
    -off
    -15.69
    .Blocks
    -15.56
    ites
    -15.44
    igar
    -15.31
    uis
    -15.25
    啫
    -15.13
    POSITIVE LOGITS
    endor
    13.19
    imeType
    12.88
    llib
    12.56
    eil
    12.38
    管辖
    12.06
    AxisAlignment
    11.75
    原件
    11.69
    lec
    11.56
    ره
    11.50
    Signing
    11.44
    Activations Density 0.008%

    No Known Activations