© 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. 16992
    Prev
    Next
    INDEX
    Explanations

    zip code

    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
     Gee
    -0.09
     Vall
    -0.08
     foc
    -0.07
     Pont
    -0.07
     ener
    -0.06
    rops
    -0.06
     arose
    -0.06
    emotion
    -0.06
     externally
    -0.06
     Dro
    -0.06
    POSITIVE LOGITS
    blo
    0.12
     Usa
    0.12
     Zip
    0.12
    erdale
    0.12
    Zip
    0.12
    -hooks
    0.12
     Télé
    0.11
    inde
    0.11
    brook
    0.11
    kö
    0.11
    Activations Density 0.263%

    No Known Activations