© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48506
    Prev
    Next
    INDEX
    Explanations

    I thought

    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
    phin
    -0.12
    adel
    -0.12
    ages
    -0.11
    uste
    -0.11
     berk
    -0.10
    Enough
    -0.10
     appeared
    -0.10
     seemingly
    -0.10
     Should
    -0.10
    774
    -0.10
    POSITIVE LOGITS
     surely
    0.12
     everybody
    0.12
     Cros
    0.09
     maybe
    0.09
     only
    0.09
     Hass
    0.09
     everyone
    0.08
    ester
    0.08
    sure
    0.08
     Pais
    0.08
    Activations Density 0.023%

    No Known Activations