© 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. 14704
    Prev
    Next
    INDEX
    Explanations

    newline

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

    No Comments

    Negative Logits
    Sanders
    -16.38
    .hibernate
    -15.81
    _tls
    -15.75
    newsletter
    -15.38
    .kafka
    -14.94
     carpet
    -14.44
    Snackbar
    -14.38
     fragmentManager
    -14.31
    cms
    -13.88
    倪
    -13.81
    POSITIVE LOGITS
    囹
    16.63
     verg
    15.81
    량
    15.44
     aboard
    15.13
     wr
    15.06
    悃
    15.06
     Rough
    14.81
    ̀
    14.63
    袷
    14.63
    egra
    14.31
    Activations Density 2.312%

    No Known Activations