© 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. 50891
    Prev
    Next
    INDEX
    Explanations

    fire contexts

    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
     burnt
    -0.13
     ashes
    -0.13
     fortunes
    -0.12
    IDGET
    -0.11
     Burn
    -0.11
     lav
    -0.11
     celebrated
    -0.11
    abis
    -0.10
    exist
    -0.10
    ourt
    -0.10
    POSITIVE LOGITS
     jog
    0.09
    PEG
    0.09
    jak
    0.08
     Jog
    0.08
    rine
    0.08
    rite
    0.08
     minimalist
    0.08
     Abbott
    0.08
     intuitive
    0.08
    dll
    0.07
    Activations Density 0.001%

    No Known Activations