© 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. 116977
    Prev
    Next
    INDEX
    Explanations

    scientific research and findings

    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
     paperwork
    -0.09
     Tent
    -0.09
    Collapse
    -0.09
     Burl
    -0.08
     disappoint
    -0.08
     deserving
    -0.08
    terminated
    -0.08
     troublesome
    -0.08
     Sick
    -0.08
    ivent
    -0.08
    POSITIVE LOGITS
     scientifically
    0.44
     psychologists
    0.35
     scientific
    0.33
     neuroscience
    0.33
     psychologically
    0.32
     psychology
    0.32
     psychologist
    0.31
    scientific
    0.31
     scientists
    0.30
     Scientific
    0.30
    Activations Density 0.241%

    No Known Activations