© 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. 31003
    Prev
    Next
    INDEX
    Explanations

    make a sandwich

    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
     smiling
    -0.10
     friendship
    -0.10
    ivi
    -0.10
     rapport
    -0.09
     fucking
    -0.09
     muchas
    -0.09
     comfortably
    -0.09
     Leisure
    -0.09
     crunch
    -0.09
     Mell
    -0.09
    POSITIVE LOGITS
     blind
    0.18
     scav
    0.15
     Blind
    0.14
     yourselves
    0.14
    blind
    0.14
    -blind
    0.12
     surprise
    0.12
     randomly
    0.12
     unexpected
    0.12
     pretended
    0.12
    Activations Density 0.022%

    No Known Activations