© 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. 49637
    Prev
    Next
    INDEX
    Explanations

    number format or codes

    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
     Neal
    -0.11
    aleigh
    -0.10
     Furn
    -0.10
    elas
    -0.10
     blo
    -0.09
    cab
    -0.09
    omo
    -0.09
    Cab
    -0.09
     fortunes
    -0.09
     volcanic
    -0.09
    POSITIVE LOGITS
     Shoot
    0.09
     rigor
    0.09
    ett
    0.09
     Filip
    0.09
    shoot
    0.08
    isman
    0.08
     Zar
    0.08
     Harding
    0.08
     afflicted
    0.08
     Yug
    0.08
    Activations Density 0.022%

    No Known Activations