© 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. 90568
    Prev
    Next
    INDEX
    Explanations

    while followed by -ing verbs

    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
    underscore
    -0.10
    cko
    -0.09
    isser
    -0.09
     Serg
    -0.09
     embark
    -0.09
     recognised
    -0.09
    bor
    -0.09
     Plain
    -0.09
     elsewhere
    -0.09
    icol
    -0.09
    POSITIVE LOGITS
     keeping
    0.19
     holding
    0.17
     maintaining
    0.17
     retaining
    0.14
     adher
    0.14
     bearing
    0.14
     avoiding
    0.14
     omit
    0.14
     staying
    0.13
     bypass
    0.13
    Activations Density 0.113%

    No Known Activations