© 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. 3635
    Prev
    Next
    INDEX
    Explanations

    taking from a source

    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
     horsepower
    -0.11
    uran
    -0.11
    tty
    -0.10
     linger
    -0.10
     bookmark
    -0.10
    zer
    -0.10
    linger
    -0.10
     POLITICO
    -0.10
    cert
    -0.10
     favor
    -0.10
    POSITIVE LOGITS
     rightful
    0.13
     defeated
    0.12
     unsus
    0.11
     conquered
    0.10
     offices
    0.10
     guarded
    0.10
     classrooms
    0.10
     consenting
    0.09
     Sof
    0.09
     labs
    0.09
    Activations Density 0.279%

    No Known Activations