© 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. 92010
    Prev
    Next
    INDEX
    Explanations

    date: April

    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
    lse
    -0.10
     bluff
    -0.09
     Boyd
    -0.09
    reo
    -0.09
     Marketable
    -0.09
    vc
    -0.09
    ffset
    -0.08
     informal
    -0.08
     recession
    -0.08
     restructuring
    -0.08
    POSITIVE LOGITS
     woven
    0.13
     hung
    0.11
     spun
    0.10
     weave
    0.10
     PIE
    0.09
     yarn
    0.09
     quilt
    0.09
     hangs
    0.09
     tape
    0.09
     pie
    0.09
    Activations Density 0.001%

    No Known Activations