© 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. 2362
    Prev
    Next
    INDEX
    Explanations

    段

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

    No Comments

    Negative Logits
    lan
    -18.75
     mer
    -17.38
     Regina
    -17.00
    emer
    -15.69
    Mer
    -15.69
    Merit
    -15.63
     Mer
    -15.56
    ąż
    -15.50
    META
    -15.44
     Simmons
    -15.31
    POSITIVE LOGITS
    段
    36.50
     rad
    23.88
    _pres
    19.50
    暂
    19.25
    一段
    19.13
    -rad
    19.00
    rad
    18.88
    这段
    18.88
    .rad
    18.88
    范
    18.63
    Activations Density 0.074%

    No Known Activations