© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114210
    Prev
    Next
    INDEX
    Explanations

    licensing and code structure

    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
    Ey
    -0.10
    spa
    -0.09
     Tent
    -0.09
     calam
    -0.08
     Shen
    -0.08
    fe
    -0.07
    sp
    -0.07
     Ey
    -0.07
    own
    -0.07
    sek
    -0.07
    POSITIVE LOGITS
     oro
    0.11
    inci
    0.11
     COMMENTS
    0.11
    edi
    0.11
     oceans
    0.11
     expended
    0.10
     sle
    0.10
    lical
    0.10
    emet
    0.10
    ritis
    0.10
    Activations Density 0.006%

    No Known Activations