© 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. 5629
    Prev
    Next
    INDEX
    Explanations

    compliance with rules

    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
    -www
    -0.11
     corruption
    -0.11
     hob
    -0.11
     Cooke
    -0.11
    acd
    -0.11
    305
    -0.11
    weg
    -0.11
     jane
    -0.10
     unn
    -0.10
     Dok
    -0.10
    POSITIVE LOGITS
     compliance
    0.16
     comply
    0.15
     compliant
    0.13
     complying
    0.13
     Viol
    0.12
     Compliance
    0.11
     conform
    0.11
     conformity
    0.10
     violations
    0.10
     adhere
    0.10
    Activations Density 0.220%

    No Known Activations