© 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. 30513
    Prev
    Next
    INDEX
    Explanations

    usual, expected, or habitual actions

    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
     Kind
    -0.11
    expo
    -0.10
    Kind
    -0.10
    meer
    -0.09
    --+
    -0.09
    juan
    -0.09
     Worst
    -0.09
    emes
    -0.09
    /qu
    -0.09
    hind
    -0.09
    POSITIVE LOGITS
     routine
    0.23
     weekly
    0.20
     routines
    0.18
     regular
    0.18
     yearly
    0.16
     routinely
    0.16
     monthly
    0.16
     usual
    0.16
     daily
    0.16
     habitual
    0.16
    Activations Density 0.079%

    No Known Activations