© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 92230
    Prev
    Next
    INDEX
    Explanations

    win, victory, or defeat

    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
    Not in Any Lists

    No Comments

    Negative Logits
     corrections
    -0.08
     therap
    -0.08
    886
    -0.08
    bra
    -0.07
     Deadly
    -0.07
     Stern
    -0.07
    rels
    -0.07
     fert
    -0.07
    iples
    -0.07
    bitset
    -0.07
    POSITIVE LOGITS
     victory
    0.67
     winning
    0.66
     wins
    0.59
     victorious
    0.58
     victories
    0.57
     win
    0.57
     defeat
    0.56
     Winning
    0.56
     winner
    0.54
     winners
    0.54
    Activations Density 0.225%

    No Known Activations