© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46079
    Prev
    Next
    INDEX
    Explanations

    Todd as a name

    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
    Negative Logits
    rices
    -0.10
    owych
    -0.10
    haul
    -0.10
     embr
    -0.09
    atters
    -0.09
    rics
    -0.09
    riers
    -0.09
    ppard
    -0.09
    encing
    -0.09
    pare
    -0.09
    POSITIVE LOGITS
    ler
    0.13
    ington
    0.12
    hunter
    0.11
    led
    0.09
    ook
    0.08
    olist
    0.08
    avia
    0.08
    yc
    0.08
    ampoo
    0.08
    lers
    0.08
    Activations Density 0.013%

    No Known Activations