© 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. 49838
    Prev
    Next
    INDEX
    Explanations

    contractions followed by a word

    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
    'e
    -0.10
     targ
    -0.10
    eri
    -0.10
     Prospect
    -0.10
     tang
    -0.10
     Cla
    -0.09
    iti
    -0.09
    erie
    -0.09
     Weber
    -0.09
    -it
    -0.09
    POSITIVE LOGITS
    gether
    0.10
    cour
    0.08
    udio
    0.08
    itionally
    0.08
     indeed
    0.08
     Indeed
    0.08
    inde
    0.08
    theless
    0.08
    azÄĥ
    0.08
    arel
    0.08
    Activations Density 0.017%

    No Known Activations