© 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. 29646
    Prev
    Next
    INDEX
    Explanations

    principle of war

    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
     hoped
    -0.10
    inton
    -0.09
     hopes
    -0.09
     desired
    -0.09
     Lah
    -0.09
    Fuse
    -0.09
     Ramp
    -0.08
     median
    -0.08
    desired
    -0.08
    439
    -0.08
    POSITIVE LOGITS
     rule
    0.54
     Rule
    0.50
     rules
    0.46
    Rule
    0.44
    rule
    0.42
     RULE
    0.42
     Rules
    0.39
    -rule
    0.38
    RULE
    0.37
    rules
    0.36
    Activations Density 0.223%

    No Known Activations