© 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. 16445
    Prev
    Next
    INDEX
    Explanations

    Steph/Stef/Stephen names

    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
    ubo
    -0.10
     infinit
    -0.09
    ivia
    -0.09
    ishi
    -0.09
    eing
    -0.08
    ees
    -0.08
    ær
    -0.08
    illow
    -0.08
     impro
    -0.08
     veh
    -0.08
    POSITIVE LOGITS
    enson
    0.13
    ansson
    0.11
    ano
    0.10
    anness
    0.10
    iej
    0.10
    saida
    0.09
     Myth
    0.09
    ãģķ
    0.09
    ania
    0.09
     sims
    0.09
    Activations Density 0.010%

    No Known Activations