© 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. 116029
    Prev
    Next
    INDEX
    Explanations

    trained professionals

    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
     controversial
    -0.10
     provisional
    -0.09
     Minority
    -0.09
     fascinating
    -0.09
     obsolete
    -0.09
    agem
    -0.08
     secs
    -0.08
     proudly
    -0.08
     anonymous
    -0.08
    ilib
    -0.08
    POSITIVE LOGITS
     full
    0.19
     trained
    0.19
     seasoned
    0.18
     reinforced
    0.16
    trained
    0.15
     skilled
    0.15
     experienced
    0.14
     professional
    0.14
     fortified
    0.14
     concerted
    0.14
    Activations Density 0.211%

    No Known Activations