© 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. 48711
    Prev
    Next
    INDEX
    Explanations

    spherical shapes and dimensions

    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
     folded
    -0.14
     folding
    -0.13
     strip
    -0.12
     fold
    -0.12
     Fold
    -0.12
     bend
    -0.12
    fold
    -0.12
     blades
    -0.12
    -length
    -0.11
    -fold
    -0.11
    POSITIVE LOGITS
     sphere
    0.23
     spherical
    0.23
     spheres
    0.23
     diameter
    0.22
     Diameter
    0.21
     Sphere
    0.20
    sphere
    0.19
     size
    0.19
    Sphere
    0.18
     ball
    0.18
    Activations Density 0.932%

    No Known Activations