© 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. 8192
    Prev
    Next
    INDEX
    Explanations

    sacrifice and expense

    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
    Negative Logits
     Provision
    -0.11
    oint
    -0.10
     bulky
    -0.10
     sund
    -0.09
     Irving
    -0.09
    zin
    -0.09
    [model
    -0.09
     provisional
    -0.09
    ubo
    -0.09
    _FD
    -0.08
    POSITIVE LOGITS
     sacrifice
    0.16
     sacrifices
    0.14
     sacrificing
    0.13
     Sacr
    0.13
     sacrificed
    0.12
     sac
    0.11
     compromises
    0.11
     sacr
    0.10
     compromise
    0.10
     sacrific
    0.10
    Activations Density 0.184%

    No Known Activations