© 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. 2849
    Prev
    Next
    INDEX
    Explanations

    say mol

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

    No Comments

    Negative Logits
    Pres
    -25.38
     Pres
    -24.75
    pres
    -23.25
    -pres
    -22.50
    许
    -22.00
    顾
    -19.88
    .pres
    -19.75
    _pres
    -19.75
     pres
    -19.50
    CAP
    -18.88
    POSITIVE LOGITS
     mol
    50.25
     Mol
    43.50
    mol
    41.25
    /mol
    36.75
    熔
    33.75
     melts
    29.13
     melt
    28.75
     melting
    27.75
     molt
    27.25
     Mel
    26.75
    Activations Density 0.044%

    No Known Activations