© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 61519
    Prev
    Next
    INDEX
    Explanations

    -wise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crossing
    -0.09
     wakes
    -0.09
    pta
    -0.09
    GENER
    -0.09
    suit
    -0.08
    Headers
    -0.08
    ovan
    -0.08
     batch
    -0.08
     Strand
    -0.08
     isl
    -0.08
    POSITIVE LOGITS
    (SC
    0.08
    abling
    0.08
     wise
    0.08
    zym
    0.08
    .bi
    0.08
    iring
    0.08
     Trophy
    0.08
    dur
    0.08
     discrimination
    0.08
    -wise
    0.08
    Activations Density 0.042%

    No Known Activations