© 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. 3577
    Prev
    Next
    INDEX
    Explanations

    numbers followed by duration or quantity

    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
     charming
    -0.10
     loung
    -0.10
     Plug
    -0.10
    apore
    -0.10
     underground
    -0.10
     immortal
    -0.10
     Rom
    -0.10
     Manning
    -0.10
    ofday
    -0.10
     halls
    -0.10
    POSITIVE LOGITS
     punishing
    0.13
     merciless
    0.13
     harder
    0.11
     targeting
    0.11
     punish
    0.11
     flank
    0.11
     hitting
    0.10
     strikes
    0.10
     inflict
    0.10
     evenly
    0.10
    Activations Density 0.016%

    No Known Activations