© 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. 16865
    Prev
    Next
    INDEX
    Explanations

    circle and circular shapes

    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
    .drawLine
    -0.12
    strap
    -0.11
    chip
    -0.10
     linear
    -0.10
     claws
    -0.10
     slit
    -0.10
    .fillRect
    -0.10
     Kore
    -0.10
    box
    -0.10
     claw
    -0.10
    POSITIVE LOGITS
     circle
    0.40
     circular
    0.40
     circles
    0.37
     Circular
    0.36
     Circle
    0.34
    circle
    0.33
    Circle
    0.32
    -circle
    0.32
    Circular
    0.31
    (circle
    0.30
    Activations Density 0.606%

    No Known Activations