© 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. 29551
    Prev
    Next
    INDEX
    Explanations

    location or data store

    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
    —they
    -0.11
     (=
    -0.11
    insky
    -0.10
     “âĢ¦
    -0.10
    163
    -0.10
    NECT
    -0.10
     Olson
    -0.10
    —all
    -0.10
     helicopt
    -0.10
     schle
    -0.10
    POSITIVE LOGITS
     briefly
    0.10
     extensively
    0.10
     comparatively
    0.09
     potentially
    0.09
     remotely
    0.09
     universally
    0.09
     externally
    0.09
     indirectly
    0.09
     internally
    0.09
    azo
    0.09
    Activations Density 0.856%

    No Known Activations