© 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. 116435
    Prev
    Next
    INDEX
    Explanations

    Redistributions of source code must

    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
     purch
    -0.11
     SPD
    -0.11
    vr
    -0.11
     invol
    -0.10
     lur
    -0.10
     neighb
    -0.10
    ursal
    -0.09
    ikan
    -0.09
     Sund
    -0.09
    strand
    -0.09
    POSITIVE LOGITS
     Lotus
    0.11
     Nes
    0.09
     Gow
    0.09
     ere
    0.09
     Narrow
    0.09
     conceptual
    0.08
    ancia
    0.08
     unleashed
    0.08
     theoretical
    0.08
     burst
    0.08
    Activations Density 0.001%

    No Known Activations