© 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. 115498
    Prev
    Next
    INDEX
    Explanations

    former graduates

    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
     trif
    -0.09
    zzo
    -0.09
    irement
    -0.09
    rear
    -0.08
    aget
    -0.08
     triang
    -0.08
     Zimmer
    -0.08
     ad
    -0.08
     coded
    -0.08
     planners
    -0.07
    POSITIVE LOGITS
     intellig
    0.12
     Hoch
    0.11
    º«
    0.11
    former
    0.11
     anyways
    0.10
     Mond
    0.10
     Amit
    0.09
     onward
    0.09
     former
    0.09
     graduates
    0.09
    Activations Density 0.005%

    No Known Activations