© 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. 15411
    Prev
    Next
    INDEX
    Explanations

    say 7

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

    No Comments

    Negative Logits
     portraits
    -15.94
     sixteen
    -15.25
     portrait
    -14.88
    五四
    -14.75
    apis
    -14.44
    orners
    -14.31
    腰
    -14.13
    脐
    -14.13
     zip
    -13.81
    六
    -13.56
    POSITIVE LOGITS
    seven
    18.38
    ugh
    17.63
    lug
    17.50
    七个
    17.25
    7
    16.75
    reu
    16.50
     seven
    16.38
     seventh
    16.25
    bau
    16.00
    rew
    15.94
    Activations Density 0.015%

    No Known Activations