© 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. 112176
    Prev
    Next
    INDEX
    Explanations

    discourse 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
     plac
    -0.11
     percept
    -0.10
     aesthetic
    -0.10
     stub
    -0.10
     resp
    -0.09
     contempl
    -0.09
    COPE
    -0.09
     adaptation
    -0.09
     emotional
    -0.09
     ecosystem
    -0.09
    POSITIVE LOGITS
     Fou
    0.26
     disc
    0.17
     discourse
    0.16
     Disc
    0.16
    /disc
    0.13
    Disc
    0.13
     practices
    0.13
    -disc
    0.13
     Discipline
    0.13
    disciplinary
    0.12
    Activations Density 0.102%

    No Known Activations