© 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. 14466
    Prev
    Next
    INDEX
    Explanations

    say burn

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

    No Comments

    Negative Logits
    vect
    -18.25
    distribution
    -18.25
    Vect
    -17.25
    .Dao
    -17.13
     DISTRIBUT
    -16.63
     Distribution
    -16.50
    图画
    -16.50
    宦
    -16.38
     addChild
    -16.25
     distribution
    -16.13
    POSITIVE LOGITS
    pear
    16.38
    烧
    15.94
    火
    15.50
     Burning
    14.75
    质量
    14.50
    standing
    14.38
     burn
    14.25
     ph
    14.25
     Burn
    14.06
     erreur
    13.88
    Activations Density 0.067%

    No Known Activations