© 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. 1771
    Prev
    Next
    INDEX
    Explanations

    [speech] => [language]

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

    No Comments

    Negative Logits
     speech
    -36.50
    Speech
    -34.50
     speak
    -34.50
     Speech
    -33.75
     speakers
    -31.88
    speech
    -31.38
     speaks
    -31.00
     speaking
    -30.63
     spoke
    -30.50
     Speak
    -29.88
    POSITIVE LOGITS
    材料
    18.50
    คาร
    17.38
     matrix
    17.25
    Json
    17.00
    陣
    16.88
    矩阵
    16.75
     materials
    16.25
     matriz
    15.88
     matrices
    15.75
     Json
    15.69
    Activations Density 0.134%

    No Known Activations