© 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. 30584
    Prev
    Next
    INDEX
    Explanations

    award nominations

    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
     Prism
    -0.11
     Blow
    -0.10
     Fet
    -0.10
    enville
    -0.10
    inel
    -0.09
    ennen
    -0.09
     discrete
    -0.09
     Neck
    -0.09
     LOOP
    -0.09
    iglia
    -0.09
    POSITIVE LOGITS
    enes
    0.09
     contempor
    0.09
     stub
    0.08
     Erd
    0.08
     energ
    0.08
    -buffer
    0.08
     td
    0.08
     TD
    0.08
     Maj
    0.08
    Compare
    0.08
    Activations Density 0.018%

    No Known Activations