© 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. 2413
    Prev
    Next
    INDEX
    Explanations

    徐

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

    No Comments

    Negative Logits
    SEG
    -20.63
    _SEG
    -20.50
    esty
    -17.25
    legg
    -17.25
    seg
    -16.63
    _seg
    -16.50
    legend
    -16.13
    Leg
    -16.13
     seg
    -15.94
    istine
    -15.69
    POSITIVE LOGITS
    徐
    81.50
     Mic
    58.50
     mic
    56.75
    Mic
    54.75
     μ
    52.25
     Mur
    47.00
    μ
    46.50
    Mur
    44.00
     mu
    41.25
    mic
    40.75
    Activations Density 0.066%

    No Known Activations