© 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. 7565
    Prev
    Next
    INDEX
    Explanations

    known as

    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
     Gong
    -0.10
    vas
    -0.10
     perennial
    -0.10
     polyester
    -0.10
    isty
    -0.10
    /rs
    -0.10
    ↵↵↵↵↵↵
    -0.10
     Granite
    -0.10
     progressives
    -0.10
     mirrored
    -0.09
    POSITIVE LOGITS
     likewise
    0.11
     uploading
    0.10
     uploads
    0.10
     Wiki
    0.10
     uploaded
    0.10
     alongside
    0.09
     wiki
    0.09
     Instagram
    0.09
     net
    0.09
     Uploaded
    0.09
    Activations Density 0.111%

    No Known Activations