© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3221
    Prev
    Next
    INDEX
    Explanations

    [entry] => [entry]

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    _factors
    -16.75
     communities
    -16.63
    彦
    -16.63
    problem
    -16.63
    _signal
    -16.00
    社区
    -15.94
    eworld
    -15.31
    signal
    -15.19
    .nt
    -15.06
    _FACTOR
    -14.88
    POSITIVE LOGITS
     entry
    75.00
     Entry
    70.00
    entry
    69.00
    Entry
    66.00
    (entry
    65.00
    	entry
    64.00
    _entry
    62.50
    .entry
    62.25
    -entry
    58.50
     ENTRY
    55.25
    Activations Density 0.161%

    No Known Activations