© 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. 16136
    Prev
    Next
    INDEX
    Explanations

    works out

    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
    .âĢ¢
    -0.10
    <|fim_suffix|>
    -0.10
    chio
    -0.09
     suc
    -0.09
     lust
    -0.09
    /tool
    -0.08
     McCart
    -0.08
     OH
    -0.08
     singled
    -0.08
    اØ
    -0.08
    POSITIVE LOGITS
     is
    0.11
    unately
    0.10
     refers
    0.10
    fortunately
    0.09
    owe
    0.09
    jong
    0.09
     anybody
    0.09
    orget
    0.09
     notwithstanding
    0.08
    !/
    0.08
    Activations Density 0.023%

    No Known Activations