© 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. 33390
    Prev
    Next
    INDEX
    Explanations

    Yuri and Ivan 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
    омеÑĢ
    -0.11
    åĬ¡
    -0.11
     Celtic
    -0.11
    sville
    -0.10
    al
    -0.10
     Rory
    -0.10
    plain
    -0.10
     Viv
    -0.10
     iter
    -0.10
    âĸĪ
    -0.10
    POSITIVE LOGITS
     Federation
    0.12
    hoe
    0.12
    oooo
    0.09
     federation
    0.08
    ogle
    0.08
     coup
    0.08
    y
    0.08
     olig
    0.08
     Putin
    0.08
     Bolshevik
    0.07
    Activations Density 0.109%

    No Known Activations