© 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. 17212
    Prev
    Next
    INDEX
    Explanations

    in, on, from

    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
    wer
    -0.06
    wed
    -0.06
    otton
    -0.06
     protr
    -0.06
     international
    -0.06
     modern
    -0.05
     bottom
    -0.05
     Berm
    -0.05
     upt
    -0.05
     supermarket
    -0.05
    POSITIVE LOGITS
    omba
    0.13
     resil
    0.12
     scrut
    0.12
     misunder
    0.11
    maf
    0.11
    eworthy
    0.11
    ennen
    0.11
    acas
    0.11
    /ac
    0.11
     Preston
    0.11
    Activations Density 0.860%

    No Known Activations