© 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. 32134
    Prev
    Next
    INDEX
    Explanations

    to rent, must be, to work, to relocate, to pay, to search, to leave

    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
     Buen
    -0.11
     patent
    -0.09
    lopen
    -0.09
     shrinking
    -0.09
     tink
    -0.09
     Shank
    -0.08
     wink
    -0.08
     dying
    -0.08
    ify
    -0.08
     spotted
    -0.08
    POSITIVE LOGITS
     contend
    0.13
     wait
    0.13
     rely
    0.13
     await
    0.13
     scramble
    0.11
     relied
    0.11
     relies
    0.11
     abandon
    0.10
    /ng
    0.10
    Ng
    0.10
    Activations Density 0.140%

    No Known Activations