© 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. 114569
    Prev
    Next
    INDEX
    Explanations

    following instructions or commands

    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
    istra
    -0.11
     Tran
    -0.10
     afternoon
    -0.10
    VERTEX
    -0.09
     Toll
    -0.09
     Glo
    -0.09
    opi
    -0.09
     Jong
    -0.09
    .wrap
    -0.09
     lia
    -0.09
    POSITIVE LOGITS
     obey
    0.60
     comply
    0.49
     obedience
    0.49
     complying
    0.49
     obedient
    0.48
     compliance
    0.47
     complied
    0.46
     obe
    0.46
     compliant
    0.40
     Compliance
    0.39
    Activations Density 0.253%

    No Known Activations