© 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. 112113
    Prev
    Next
    INDEX
    Explanations

    keyboard layouts

    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
     grinned
    -0.11
     smile
    -0.11
     smiling
    -0.11
     grin
    -0.11
     smiles
    -0.10
     Smile
    -0.10
     smiled
    -0.09
     Reeves
    -0.08
    umbs
    -0.08
     Strom
    -0.08
    POSITIVE LOGITS
     Fond
    0.11
    wort
    0.11
     Tit
    0.11
    Tit
    0.11
    antis
    0.11
     softened
    0.11
     Sole
    0.10
     responding
    0.10
    onaut
    0.10
     touched
    0.10
    Activations Density 0.008%

    No Known Activations