© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32144
    Prev
    Next
    INDEX
    Explanations

    action words ending in -ing or with past tense endings

    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
     authorised
    -0.16
     specialised
    -0.16
     personalised
    -0.15
     organisations
    -0.15
     minimise
    -0.15
     initialised
    -0.15
     organised
    -0.14
     initialise
    -0.14
     organisers
    -0.14
     analys
    -0.14
    POSITIVE LOGITS
     round
    0.14
     patron
    0.10
    gross
    0.10
     horribly
    0.10
     Round
    0.10
     ROUND
    0.10
    -Za
    0.10
    ottie
    0.10
     Carol
    0.09
     Oregon
    0.09
    Activations Density 0.058%

    No Known Activations