© 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. 4804
    Prev
    Next
    INDEX
    Explanations

    quantitative changes

    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
    397
    -0.10
    WER
    -0.09
    051
    -0.09
    ä¸
    -0.08
    werk
    -0.08
     Wer
    -0.08
     Chick
    -0.08
     Sor
    -0.08
     MER
    -0.08
     lasting
    -0.07
    POSITIVE LOGITS
     considerably
    0.27
     substantially
    0.22
     accordingly
    0.20
     significantly
    0.20
     drastically
    0.19
     dramatically
    0.19
     enormously
    0.19
     markedly
    0.19
     exponentially
    0.19
     slightly
    0.17
    Activations Density 0.300%

    No Known Activations