© 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. 13962
    Prev
    Next
    INDEX
    Explanations

    self-description and states

    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
     horr
    -0.09
     Waterloo
    -0.09
    [Index
    -0.09
     /.
    -0.09
     Flush
    -0.09
     condom
    -0.08
    orado
    -0.08
    Flush
    -0.08
     inset
    -0.08
     hoped
    -0.08
    POSITIVE LOGITS
     born
    0.16
     Born
    0.14
    Born
    0.14
     multif
    0.14
     ðĿ
    0.13
     ðŁ
    0.12
     passionate
    0.12
     embody
    0.12
    Greetings
    0.12
     graduated
    0.12
    Activations Density 0.055%

    No Known Activations