© 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. 117276
    Prev
    Next
    INDEX
    Explanations

    applicable laws and regulations

    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
     Brig
    -0.11
    argin
    -0.11
     Briggs
    -0.11
    pedia
    -0.11
    iri
    -0.10
     bq
    -0.10
    andr
    -0.10
    andin
    -0.09
     Kund
    -0.09
    alia
    -0.09
    POSITIVE LOGITS
     applicable
    0.10
     lawful
    0.09
     laws
    0.09
    avec
    0.09
     McCart
    0.09
     tape
    0.09
     dizzy
    0.09
    tape
    0.08
     criminal
    0.08
     statutes
    0.08
    Activations Density 0.036%

    No Known Activations