© 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. 3772
    Prev
    Next
    INDEX
    Explanations

    comma separation

    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
    riel
    -0.11
    otech
    -0.09
    ugu
    -0.08
     nonexistent
    -0.08
     whats
    -0.08
    oga
    -0.08
     Ariel
    -0.07
    erte
    -0.07
     supposed
    -0.07
     Ari
    -0.07
    POSITIVE LOGITS
     paradox
    0.14
     impro
    0.12
     alas
    0.12
     ah
    0.11
     uh
    0.11
     indeed
    0.11
     hey
    0.11
    quan
    0.11
     amen
    0.11
     frankly
    0.10
    Activations Density 0.087%

    No Known Activations