© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 25033
    Prev
    Next
    INDEX
    Explanations

    winning, losing, or succeeding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     worldly
    -0.10
     Cue
    -0.10
     implic
    -0.09
    quiv
    -0.09
     íĺ
    -0.09
    rio
    -0.09
    -none
    -0.09
    -aged
    -0.09
    OLON
    -0.09
     balk
    -0.09
    POSITIVE LOGITS
     victory
    0.16
     defeat
    0.14
     victories
    0.12
     dominance
    0.11
     winning
    0.11
     derby
    0.11
     Victory
    0.11
     undefeated
    0.11
     reversal
    0.10
     defeats
    0.10
    Activations Density 0.125%

    No Known Activations