© 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. 50794
    Prev
    Next
    INDEX
    Explanations

    consuming

    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
    eki
    -0.12
    458
    -0.10
     Horny
    -0.10
    furt
    -0.09
     delic
    -0.09
     commodities
    -0.09
    744
    -0.08
     misc
    -0.08
    FACT
    -0.08
    Broadcast
    -0.08
    POSITIVE LOGITS
     flames
    0.16
     fires
    0.14
     blaze
    0.13
     fire
    0.13
     wildfire
    0.13
     occupied
    0.12
     wildfires
    0.12
     darkness
    0.12
     Alive
    0.11
     passion
    0.11
    Activations Density 0.007%

    No Known Activations