© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1975
    Prev
    Next
    INDEX
    Explanations

    license boilerplate

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

    No Comments

    Negative Logits
    崛
    -18.63
    INTEGER
    -17.75
     Evo
    -17.50
    chu
    -17.38
    IRA
    -17.25
     Melania
    -17.00
    ��
    -17.00
    IBLE
    -16.88
    FFE
    -16.75
    rena
    -16.63
    POSITIVE LOGITS
    text
    17.38
    书画
    15.88
     texto
    15.69
     text
    15.13
     en
    14.38
     carbon
    14.06
    绘画
    13.63
    文学
    13.25
    钢
    13.13
    _sql
    13.00
    Activations Density 0.634%

    No Known Activations