© 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. 14433
    Prev
    Next
    INDEX
    Explanations

    => 6

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

    No Comments

    Negative Logits
     Tory
    -19.13
    shal
    -17.25
    lington
    -17.00
    alien
    -16.63
     unicorn
    -16.50
    vinc
    -16.38
    bery
    -16.25
    仝
    -16.25
    olic
    -16.25
    ton
    -16.00
    POSITIVE LOGITS
    еле
    15.69
    есс
    15.56
    asure
    15.00
    いけ
    14.38
    下巴
    14.25
    uze
    13.81
     Carr
    13.69
    メ
    13.69
    caf
    13.56
    rad
    13.44
    Activations Density 0.082%

    No Known Activations