© 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. 115766
    Prev
    Next
    INDEX
    Explanations

    actions involving taking or seeking something

    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
     minded
    -0.10
    ersed
    -0.09
    ertz
    -0.09
    dea
    -0.09
    ark
    -0.08
    ensch
    -0.08
    gh
    -0.08
     temptation
    -0.08
    woke
    -0.08
     *_
    -0.08
    POSITIVE LOGITS
     neighbours
    0.11
     entire
    0.11
     wife
    0.10
     unsuccessfully
    0.10
    /respond
    0.10
     twice
    0.09
    ampp
    0.09
     neighbour
    0.09
     repeatedly
    0.09
     Twice
    0.09
    Activations Density 0.021%

    No Known Activations