© 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. 89230
    Prev
    Next
    INDEX
    Explanations

    convention, disclaimer, Providence

    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
     Grape
    -0.09
     Jame
    -0.08
     Lew
    -0.08
    onet
    -0.08
    cone
    -0.08
     OCI
    -0.08
    ailles
    -0.08
    pta
    -0.08
     sign
    -0.08
    hoa
    -0.08
    POSITIVE LOGITS
     bury
    0.10
    inas
    0.10
     indexes
    0.09
    ago
    0.09
    :NO
    0.09
     jumper
    0.09
     ÑĥÑģп
    0.09
    oggled
    0.09
    .travel
    0.09
     '\\'
    0.09
    Activations Density 0.001%

    No Known Activations