© 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. 47260
    Prev
    Next
    INDEX
    Explanations

    Permission to any person obtaining

    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
    aron
    -0.09
     sach
    -0.09
     Liqu
    -0.09
    alon
    -0.09
    alem
    -0.09
    illon
    -0.09
    avax
    -0.09
    itals
    -0.08
     hierarchical
    -0.08
     hier
    -0.08
    POSITIVE LOGITS
     alright
    0.10
    eland
    0.10
     LAP
    0.09
     salts
    0.09
    planet
    0.09
     drifted
    0.09
    izo
    0.09
     admir
    0.09
    baugh
    0.08
    .lt
    0.08
    Activations Density 0.001%

    No Known Activations