© 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. 18041
    Prev
    Next
    INDEX
    Explanations

    loud, said, carefully, obvious

    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
    ardin
    -0.10
    pez
    -0.08
    imore
    -0.08
     Comedy
    -0.08
    ajar
    -0.08
     coc
    -0.08
     opposite
    -0.08
    rene
    -0.08
     requester
    -0.08
    nap
    -0.08
    POSITIVE LOGITS
     loudly
    0.12
     louder
    0.12
     loud
    0.12
     slower
    0.11
     slowly
    0.10
     differentiated
    0.10
    slow
    0.10
    anela
    0.10
     slow
    0.10
     carefully
    0.10
    Activations Density 0.011%

    No Known Activations