© 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. 26339
    Prev
    Next
    INDEX
    Explanations

    signed, also, first, worked, won, drafted

    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
     itself
    -0.10
    OK
    -0.10
     OK
    -0.09
     and
    -0.08
     themselves
    -0.08
    owl
    -0.08
    ikan
    -0.08
     Eaton
    -0.08
     zw
    -0.08
     cud
    -0.08
    POSITIVE LOGITS
    olie
    0.10
    indi
    0.10
    agnar
    0.09
     Latter
    0.09
    WX
    0.09
     Hutchinson
    0.09
     Robbie
    0.09
     scre
    0.09
    lycer
    0.09
     nós
    0.09
    Activations Density 0.054%

    No Known Activations