© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14488
    Prev
    Next
    INDEX
    Explanations

    large stone blocks

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

    No Comments

    Negative Logits
    unj
    -16.63
    .Qt
    -16.50
    .getActivity
    -16.13
    vest
    -16.13
    oyal
    -15.75
    Krist
    -15.63
    律
    -15.56
     crackers
    -15.56
    oster
    -15.50
    isel
    -15.50
    POSITIVE LOGITS
    zens
    14.63
    皱纹
    14.63
     bred
    14.50
    簿
    13.69
    zx
    13.69
     freedoms
    13.50
    borne
    13.38
    GED
    13.13
    <count
    13.00
    HEN
    12.88
    Activations Density 0.072%

    No Known Activations