© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15285
    Prev
    Next
    INDEX
    Explanations

    massacres

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

    No Comments

    Negative Logits
    连线
    -20.63
    限り
    -16.75
    -paper
    -16.75
    Fuse
    -16.63
    oba
    -16.63
    ollen
    -16.25
    界面
    -16.25
    connector
    -16.13
    occo
    -16.13
    .SQL
    -16.13
    POSITIVE LOGITS
     occupants
    11.81
    uary
    11.63
    -bedroom
    11.56
    牖
    11.56
    理工
    11.19
    sted
    11.00
    agency
    10.75
    .UseVisualStyleBackColor
    10.75
    ​
    10.63
    mates
    10.44
    Activations Density 0.083%

    No Known Activations