© 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. 111584
    Prev
    Next
    INDEX
    Explanations

    fight battles

    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
     hurry
    -0.10
    idot
    -0.09
     pending
    -0.09
     Stanton
    -0.09
     outr
    -0.08
    -gap
    -0.08
     overseeing
    -0.08
    erton
    -0.08
    dda
    -0.08
    Filtered
    -0.08
    POSITIVE LOGITS
     against
    0.21
    against
    0.20
     Against
    0.18
     fought
    0.17
     waged
    0.16
    Against
    0.16
     battles
    0.16
     unsuccessfully
    0.15
     fight
    0.15
     battled
    0.14
    Activations Density 0.296%

    No Known Activations