© 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. 30965
    Prev
    Next
    INDEX
    Explanations

    upon followed by preposition/pronoun

    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
    ly
    -0.12
    hoff
    -0.11
    ä¹Ī
    -0.11
    ual
    -0.10
    yers
    -0.10
    atics
    -0.10
    ourn
    -0.09
    tele
    -0.09
    ivol
    -0.09
    ting
    -0.09
    POSITIVE LOGITS
     occasion
    0.12
    st
    0.10
    enne
    0.10
    jury
    0.09
     arrival
    0.09
    ,on
    0.09
    eto
    0.09
    DEX
    0.09
    azz
    0.09
    eni
    0.09
    Activations Density 0.027%

    No Known Activations