© 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. 49630
    Prev
    Next
    INDEX
    Explanations

    previously, past, earlier

    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
     previous
    -0.13
     prior
    -0.11
     Previous
    -0.10
    Previous
    -0.09
     previously
    -0.09
    previous
    -0.09
     former
    -0.09
     prev
    -0.09
     predecessor
    -0.08
    mb
    -0.08
    POSITIVE LOGITS
    ebin
    0.18
    /current
    0.17
    -fashioned
    0.15
    è¿°
    0.14
    mentioned
    0.13
    iska
    0.12
     fashioned
    0.12
    imes
    0.12
    illes
    0.12
    itize
    0.12
    Activations Density 0.088%

    No Known Activations