© 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. 91125
    Prev
    Next
    INDEX
    Explanations

    Harris and associated place names

    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
    oven
    -0.09
    ikki
    -0.08
    ird
    -0.08
     RSS
    -0.08
    gra
    -0.08
     resc
    -0.08
    maj
    -0.08
    ede
    -0.08
    intelligence
    -0.07
     intelligence
    -0.07
    POSITIVE LOGITS
    ucci
    0.13
    uil
    0.10
     pul
    0.10
     Pul
    0.10
    onia
    0.10
     sque
    0.10
    burg
    0.10
     appe
    0.10
    fdb
    0.09
    relations
    0.09
    Activations Density 0.005%

    No Known Activations