© 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. 18348
    Prev
    Next
    INDEX
    Explanations

    shapes like U, V, Y, T

    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
    406
    -0.09
    onda
    -0.09
     Bearing
    -0.09
     Circular
    -0.09
    chen
    -0.08
     spiral
    -0.08
    Chuck
    -0.08
    ulations
    -0.08
    Analy
    -0.08
     circular
    -0.08
    POSITIVE LOGITS
    -shaped
    0.21
     shaped
    0.18
     shape
    0.13
     formed
    0.13
    Shape
    0.12
     convergence
    0.12
     formation
    0.11
     divergence
    0.11
    formation
    0.11
    formed
    0.11
    Activations Density 0.012%

    No Known Activations