© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 87871
    Prev
    Next
    INDEX
    Explanations

    others

    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
    Negative Logits
     MOST
    -0.10
    ãĤį
    -0.10
     hypoth
    -0.10
     presently
    -0.10
    amar
    -0.10
     hence
    -0.10
     consequently
    -0.10
    ìĤ
    -0.10
    icity
    -0.10
     OTHERWISE
    -0.09
    POSITIVE LOGITS
    -times
    0.12
     times
    0.12
     simply
    0.12
     may
    0.11
    ento
    0.09
    may
    0.09
    (ed
    0.09
    edor
    0.09
    times
    0.09
     might
    0.09
    Activations Density 0.036%

    No Known Activations