© 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. 48227
    Prev
    Next
    INDEX
    Explanations

    most

    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
    924
    -0.09
    ampo
    -0.09
    omm
    -0.09
    inar
    -0.08
     another
    -0.08
    996
    -0.08
    áŁĴáŀ
    -0.08
     miraculous
    -0.07
    oste
    -0.07
    ufe
    -0.07
    POSITIVE LOGITS
    æľĢ
    0.49
     greatest
    0.48
     hardest
    0.48
     most
    0.46
     easiest
    0.45
     quickest
    0.44
     strongest
    0.44
     fastest
    0.43
     closest
    0.43
     longest
    0.42
    Activations Density 1.141%

    No Known Activations