© 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. 14841
    Prev
    Next
    INDEX
    Explanations

    username

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

    No Comments

    Negative Logits
    ushi
    -16.00
    .tie
    -15.94
    Ao
    -15.69
    ảo
    -15.63
     pó
    -15.25
    (tid
    -15.19
    笋
    -15.06
    agic
    -15.00
     eos
    -14.94
    pdo
    -14.81
    POSITIVE LOGITS
    tr
    15.13
    tre
    14.19
    ious
    13.69
    涪
    13.63
    -dr
    13.63
    hor
    13.56
    flation
    13.56
    iled
    13.38
    intr
    13.38
    hr
    13.31
    Activations Density 0.005%

    No Known Activations