© 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. 15208
    Prev
    Next
    INDEX
    Explanations

    definition queries

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

    No Comments

    Negative Logits
    泷
    -15.88
    gio
    -15.44
    stell
    -15.44
     científico
    -15.19
     nymph
    -15.06
    _rom
    -14.69
     chimney
    -14.56
    anol
    -14.06
    PTY
    -14.00
    porto
    -14.00
    POSITIVE LOGITS
    出路
    18.63
    icos
    15.50
    熟
    15.44
     Oc
    14.81
    ounter
    14.75
    棒
    14.63
    oub
    14.56
    任
    14.50
    箱
    14.44
    icle
    14.38
    Activations Density 0.056%

    No Known Activations