© 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. 116150
    Prev
    Next
    INDEX
    Explanations

    National Parks, Oceanic, Film, Planning, Medical, Wine, Police

    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
     Worldwide
    -0.10
     worldwide
    -0.09
     bombard
    -0.09
     statewide
    -0.08
     global
    -0.08
     Peel
    -0.08
     globally
    -0.08
     internationally
    -0.08
    lest
    -0.08
    ulton
    -0.07
    POSITIVE LOGITS
    endar
    0.12
    emies
    0.12
    quirer
    0.11
     reasonably
    0.11
     writ
    0.11
    slick
    0.10
    /Grid
    0.10
     mig
    0.10
    ubar
    0.10
    obl
    0.10
    Activations Density 0.304%

    No Known Activations