© 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. 92213
    Prev
    Next
    INDEX
    Explanations

    urls, distribution, code blocks

    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
    kv
    -0.11
    obre
    -0.10
    avn
    -0.10
     Kirk
    -0.09
    oble
    -0.09
    sky
    -0.09
    kh
    -0.09
    abee
    -0.09
     rew
    -0.08
    .wik
    -0.08
    POSITIVE LOGITS
     proprietary
    0.10
     peril
    0.10
     literally
    0.09
    stown
    0.09
     “
    0.09
     Ston
    0.09
    istol
    0.09
     timeframe
    0.08
     nons
    0.08
    strap
    0.08
    Activations Density 0.001%

    No Known Activations