© 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. 14877
    Prev
    Next
    INDEX
    Explanations

    say numbers

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

    No Comments

    Negative Logits
    yleft
    -18.88
    spir
    -18.25
    еж
    -17.88
    stad
    -17.88
    itan
    -17.63
    pei
    -17.63
    upyter
    -17.63
    onta
    -17.50
    unger
    -17.13
    spark
    -17.00
    POSITIVE LOGITS
    -d
    16.13
     Ded
    15.56
    dü
    14.50
    DE
    14.44
    綦
    13.75
    ДЕ
    13.75
    din
    13.63
     hose
    13.56
     Five
    13.50
     Four
    13.38
    Activations Density 0.080%

    No Known Activations