© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1383
    Prev
    Next
    INDEX
    Explanations

    say "body parts"

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

    No Comments

    Negative Logits
     bone
    -42.50
     bones
    -40.75
    骨
    -40.25
     Bone
    -40.00
    Bone
    -37.25
    骨骼
    -36.00
    骨头
    -35.25
     Bones
    -35.00
    bones
    -31.25
    bone
    -29.75
    POSITIVE LOGITS
     MatDialog
    16.75
    唱片
    16.25
     play
    15.63
    电机
    15.50
    Church
    15.38
    security
    14.69
     security
    14.44
     Security
    14.38
     shopper
    14.38
    Security
    14.31
    Activations Density 0.093%

    No Known Activations