© 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. 88414
    Prev
    Next
    INDEX
    Explanations

    circular shapes and movement around them

    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
    ulk
    -0.10
     GAP
    -0.10
    .kode
    -0.09
     alley
    -0.09
    159
    -0.09
    asz
    -0.09
     sortable
    -0.09
     tou
    -0.09
    zin
    -0.09
     gap
    -0.09
    POSITIVE LOGITS
     around
    0.13
    around
    0.13
    Around
    0.10
     Around
    0.10
    -pattern
    0.10
    erk
    0.10
     Jeremiah
    0.10
     pattern
    0.10
     pat
    0.09
     clockwise
    0.09
    Activations Density 0.005%

    No Known Activations