© 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. 28227
    Prev
    Next
    INDEX
    Explanations

    once in a while

    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
    odata
    -0.12
     Met
    -0.10
    Met
    -0.10
    posted
    -0.10
    iac
    -0.10
    ITA
    -0.10
    inne
    -0.10
     Copy
    -0.09
    -Man
    -0.09
     Paths
    -0.09
    POSITIVE LOGITS
     once
    0.10
     ATV
    0.09
     rid
    0.08
     unanimously
    0.08
     ama
    0.08
     gloss
    0.07
     unanimous
    0.07
    onces
    0.07
    ứ
    0.07
     Bud
    0.07
    Activations Density 0.008%

    No Known Activations