© 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. 113416
    Prev
    Next
    INDEX
    Explanations

    numbers, code, and formulas

    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
     prof
    -0.10
    eing
    -0.08
     fog
    -0.08
    lei
    -0.08
     scrim
    -0.08
    Âł↵
    -0.08
     Fog
    -0.08
     gyr
    -0.08
     »,
    -0.08
     ult
    -0.08
    POSITIVE LOGITS
    amel
    0.11
    Broken
    0.10
    ,.↵↵
    0.09
    .ordinal
    0.09
     Lowe
    0.09
    839
    0.09
    andan
    0.09
    andi
    0.08
    htag
    0.08
    uku
    0.08
    Activations Density 0.037%

    No Known Activations