© 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. 27588
    Prev
    Next
    INDEX
    Explanations

    distribution of amounts

    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
     Grat
    -0.10
    ower
    -0.08
    rett
    -0.08
     Clement
    -0.08
     Cro
    -0.08
     dood
    -0.08
    د
    -0.08
    utt
    -0.08
     clipping
    -0.08
    atto
    -0.07
    POSITIVE LOGITS
     distributed
    0.21
     evenly
    0.21
     redistributed
    0.20
     mostly
    0.18
     distribute
    0.18
     distribution
    0.17
     distributing
    0.17
     spread
    0.16
     redistribute
    0.16
     distributes
    0.16
    Activations Density 0.059%

    No Known Activations