© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5531
    Prev
    Next
    INDEX
    Explanations

    in fact

    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
    elen
    -0.10
    iten
    -0.10
     (?)
    -0.10
    ).__
    -0.10
    rious
    -0.09
    231
    -0.09
    673
    -0.08
     beneath
    -0.08
    utz
    -0.08
    apan
    -0.08
    POSITIVE LOGITS
     indeed
    0.67
    inde
    0.54
     Indeed
    0.54
    Indeed
    0.52
     fact
    0.36
     actually
    0.35
     Actually
    0.32
    actually
    0.30
    Actually
    0.30
    fact
    0.25
    Activations Density 0.508%

    No Known Activations