© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1160
    Prev
    Next
    INDEX
    Explanations

    say animal names

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

    No Comments

    Negative Logits
     horse
    -44.00
     horses
    -42.50
    horse
    -40.50
     Horse
    -40.25
    马
    -39.75
    馬
    -36.00
    内马
    -31.50
    马来
    -30.38
    	slot
    -28.13
    .slot
    -27.88
    POSITIVE LOGITS
    papers
    17.63
    _rf
    16.13
    土壤
    16.00
    建筑设计
    15.31
     Paper
    15.31
    _paper
    15.25
    LogFile
    15.19
    广播
    15.00
     RF
    14.75
    WC
    14.63
    Activations Density 0.118%

    No Known Activations