© 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. 49612
    Prev
    Next
    INDEX
    Explanations

    change of state

    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
     Moff
    -0.11
    948
    -0.10
     ↵↵↵↵↵
    -0.09
    stry
    -0.09
    perc
    -0.09
     Recorder
    -0.09
    Magn
    -0.09
    antu
    -0.09
     Watt
    -0.09
    Mining
    -0.09
    POSITIVE LOGITS
     transformation
    0.35
     transformations
    0.34
     transformed
    0.31
     transform
    0.30
     transforming
    0.29
     Transformation
    0.29
     transforms
    0.28
    transform
    0.27
     Transform
    0.27
     reverted
    0.25
    Activations Density 0.382%

    No Known Activations