© 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. 2575
    Prev
    Next
    INDEX
    Explanations

    say "pres" words

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

    No Comments

    Negative Logits
    甲
    -19.88
     mods
    -17.38
     admins
    -17.00
    积分
    -16.75
    auer
    -16.63
    文明
    -16.50
    dae
    -16.25
    茭
    -15.94
    (args
    -15.88
    有机
    -15.88
    POSITIVE LOGITS
     Pres
    41.25
    Pres
    38.75
    pres
    36.00
     pres
    33.25
     PRES
    27.00
    .pres
    26.13
     presumption
    25.88
    -pres
    25.63
    preset
    24.75
    _pres
    24.50
    Activations Density 0.078%

    No Known Activations