© 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. 46506
    Prev
    Next
    INDEX
    Explanations

    strictness and formality

    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
     harmless
    -0.11
     innoc
    -0.11
    warm
    -0.11
     smoothly
    -0.11
     peacefully
    -0.11
     Friendly
    -0.11
     peaceful
    -0.11
    ibri
    -0.10
     lively
    -0.10
     warmly
    -0.10
    POSITIVE LOGITS
     stern
    0.20
     discipl
    0.18
     discipline
    0.15
     formal
    0.15
     rigid
    0.14
     Stern
    0.14
     stricter
    0.14
     disciplined
    0.14
     strict
    0.13
     severity
    0.13
    Activations Density 0.055%

    No Known Activations