© 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. 61846
    Prev
    Next
    INDEX
    Explanations

    algorithms and decisions

    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
     Blow
    -0.10
    bur
    -0.10
     dedic
    -0.10
     volcano
    -0.09
    Deadline
    -0.09
    avax
    -0.09
    ARC
    -0.09
     deadline
    -0.09
    Pic
    -0.09
     retirees
    -0.09
    POSITIVE LOGITS
     accuracy
    0.10
     biased
    0.10
     bias
    0.10
     Bias
    0.10
     biases
    0.10
     Pound
    0.09
     decisions
    0.09
     dyst
    0.09
     decision
    0.09
     mapping
    0.09
    Activations Density 0.085%

    No Known Activations