© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 3113
    Prev
    Next
    INDEX
    Explanations

    say "thought"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    (form
    -20.00
    	form
    -19.25
     form
    -18.75
    =form
    -18.63
    _form
    -18.25
    ObjectOfType
    -18.13
    .form
    -18.00
    -form
    -17.25
     endpoint
    -16.75
    类产品
    -16.75
    POSITIVE LOGITS
    思想
    42.50
    的思想
    29.13
     idea
    21.38
     input
    20.38
     ideas
    19.88
    input
    19.75
     Thought
    18.50
     thought
    18.13
    files
    18.13
     Idea
    18.00
    Activations Density 0.128%

    No Known Activations