© 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. 5910
    Prev
    Next
    INDEX
    Explanations

    css properties and font styles

    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
     upload
    -0.10
     searchable
    -0.10
     uploads
    -0.10
     uploaded
    -0.10
     Twitch
    -0.10
     Posting
    -0.09
     uploading
    -0.09
    upload
    -0.09
     posting
    -0.09
     locally
    -0.09
    POSITIVE LOGITS
     supremacy
    0.10
     recur
    0.10
     exclusive
    0.09
     scor
    0.09
    /assets
    0.09
     Archae
    0.09
    _exceptions
    0.09
    umberland
    0.09
     EFI
    0.09
    memberOf
    0.09
    Activations Density 0.025%

    No Known Activations