© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14728
    Prev
    Next
    INDEX
    Explanations

    person name

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     komm
    -17.25
    cio
    -17.13
    dsn
    -15.81
    olume
    -15.38
    Dia
    -15.13
    堡
    -15.06
     Plum
    -15.06
    ework
    -15.00
    _pins
    -15.00
    udos
    -14.88
    POSITIVE LOGITS
    afx
    15.81
    nad
    15.56
    usher
    14.81
    JR
    14.81
    trx
    14.56
    狐狸
    14.00
    电梯
    14.00
    jem
    13.75
    �
    13.69
    jr
    13.56
    Activations Density 0.432%

    No Known Activations