© 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. 88849
    Prev
    Next
    INDEX
    Explanations

    structure and discipline

    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
     boyc
    -0.10
     inaugural
    -0.10
     Vocal
    -0.09
     Innoc
    -0.09
    abe
    -0.09
    eras
    -0.09
    ORIGINAL
    -0.09
    vern
    -0.09
    _media
    -0.09
     Composite
    -0.09
    POSITIVE LOGITS
     structured
    0.39
     disciplined
    0.33
     stability
    0.33
     structure
    0.33
     orderly
    0.32
     discipline
    0.31
     Struct
    0.28
    structured
    0.28
    Structured
    0.28
     Stability
    0.27
    Activations Density 0.307%

    No Known Activations