© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115190
    Prev
    Next
    INDEX
    Explanations

    arrangement of items

    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
     dressed
    -0.09
     Dresses
    -0.09
     legs
    -0.09
     nude
    -0.08
     body
    -0.08
     verbally
    -0.08
    ROS
    -0.08
     soluble
    -0.08
     bleeding
    -0.08
    Wrapped
    -0.07
    POSITIVE LOGITS
     patterns
    0.15
     arcs
    0.13
     imitation
    0.13
     arc
    0.12
     unnatural
    0.12
     pattern
    0.12
     approximation
    0.12
     familiar
    0.12
    idot
    0.11
    wards
    0.11
    Activations Density 0.055%

    No Known Activations