© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16743
    Prev
    Next
    INDEX
    Explanations

    laws and regulations context

    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
     personally
    -0.10
     unlimited
    -0.10
     aud
    -0.10
    DU
    -0.10
     respectfully
    -0.10
     securely
    -0.09
    inese
    -0.09
    du
    -0.09
     dor
    -0.09
     elit
    -0.09
    POSITIVE LOGITS
     laws
    0.21
     jurisdictions
    0.20
     governments
    0.20
     varies
    0.19
     vary
    0.19
     varying
    0.19
     states
    0.17
     countries
    0.17
    vary
    0.16
     Governments
    0.16
    Activations Density 0.339%

    No Known Activations