© 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. 50328
    Prev
    Next
    INDEX
    Explanations

    globally and globular

    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
     adaptive
    -0.09
    pert
    -0.09
    agle
    -0.09
     puck
    -0.09
    ude
    -0.08
    aval
    -0.08
     plais
    -0.08
     roads
    -0.08
     conver
    -0.08
    tas
    -0.08
    POSITIVE LOGITS
     jeopardy
    0.11
     fet
    0.11
    unken
    0.11
    /helper
    0.10
    terr
    0.10
    anza
    0.10
     digit
    0.09
     Lantern
    0.09
    ulent
    0.09
     fascinated
    0.09
    Activations Density 0.005%

    No Known Activations