© 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. 4612
    Prev
    Next
    INDEX
    Explanations

    as followed by 'a', 'an', 'the'

    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
     Markus
    -0.08
    mond
    -0.08
    ducted
    -0.08
     Beh
    -0.07
    uki
    -0.07
     pir
    -0.07
     peg
    -0.07
     Milano
    -0.07
     vers
    -0.07
    ilm
    -0.07
    POSITIVE LOGITS
     part
    0.12
     guest
    0.11
     prisoner
    0.11
     champ
    0.10
     separate
    0.10
    engo
    0.10
     consort
    0.10
     flor
    0.10
     scheduled
    0.10
    ynchronously
    0.10
    Activations Density 0.249%

    No Known Activations