© 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. 14852
    Prev
    Next
    INDEX
    Explanations

    flower names

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

    No Comments

    Negative Logits
    Expansion
    -18.88
    expand
    -18.50
    平衡
    -16.88
    _expand
    -16.75
     Expansion
    -16.63
    Coverage
    -16.38
    _allocator
    -16.25
    Expand
    -16.13
    知己
    -15.75
     expansion
    -15.69
    POSITIVE LOGITS
    icks
    15.00
    ehr
    14.38
     programs
    14.38
    �示
    14.31
     imprison
    14.19
    coni
    13.88
     display
    13.25
     stairs
    13.25
    stairs
    13.19
    imus
    13.19
    Activations Density 0.061%

    No Known Activations