© 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. 30990
    Prev
    Next
    INDEX
    Explanations

    people and their roles

    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
     Dit
    -0.09
     Newsp
    -0.09
     Millenn
    -0.09
     clinically
    -0.09
     millennia
    -0.09
     fore
    -0.08
     Speakers
    -0.08
     tw
    -0.08
     Aerospace
    -0.08
     financially
    -0.08
    POSITIVE LOGITS
     Role
    0.19
    Role
    0.16
     Importance
    0.16
     Influence
    0.16
     Rise
    0.16
     Origins
    0.16
     Impact
    0.14
    Impact
    0.14
     Causes
    0.14
     Challenges
    0.14
    Activations Density 0.750%

    No Known Activations