© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18008
    Prev
    Next
    INDEX
    Explanations

    script execution

    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
     fran
    -0.11
     Parliamentary
    -0.10
    ByVersion
    -0.09
     Gecko
    -0.09
     perpetr
    -0.09
     mandate
    -0.09
     abandon
    -0.09
     Nep
    -0.09
     PREFIX
    -0.09
    stime
    -0.09
    POSITIVE LOGITS
    pip
    0.14
    zens
    0.12
    <<
    0.11
     Fowler
    0.09
    .chapter
    0.09
     <<
    0.09
     blogging
    0.09
     Fah
    0.09
    atom
    0.09
     casting
    0.09
    Activations Density 0.005%

    No Known Activations