© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 17038
    Prev
    Next
    INDEX
    Explanations

    complying with 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
     veto
    -0.10
     bere
    -0.10
     Supern
    -0.09
    bere
    -0.09
     DAMAGE
    -0.09
    CellValue
    -0.09
    /power
    -0.09
     specialist
    -0.09
     Patrick
    -0.08
    etre
    -0.08
    POSITIVE LOGITS
     Compliance
    0.23
     compliance
    0.22
     compliant
    0.21
     comply
    0.18
     compl
    0.16
     complied
    0.15
     complying
    0.15
     diligent
    0.12
     pursuant
    0.11
     decency
    0.11
    Activations Density 0.050%

    No Known Activations