© 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. 8279
    Prev
    Next
    INDEX
    Explanations

    making a decision

    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
    ulu
    -0.08
     busy
    -0.08
     shepherd
    -0.08
    insky
    -0.08
    inz
    -0.08
     Cree
    -0.08
    nist
    -0.08
    isclosed
    -0.07
     widely
    -0.07
    summ
    -0.07
    POSITIVE LOGITS
    ollo
    0.10
    exus
    0.10
    ous
    0.10
    lla
    0.10
    asher
    0.10
     Maker
    0.09
    ally
    0.09
    -seeking
    0.09
    tte
    0.09
    -making
    0.09
    Activations Density 0.041%

    No Known Activations