© 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. 32611
    Prev
    Next
    INDEX
    Explanations

    contractions like "i'm", "you're", "it's"

    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
     "
    -0.27
     '
    -0.23
    's
    -0.23
    're
    -0.20
    've
    -0.20
    'd
    -0.19
    'll
    -0.19
     "[
    -0.18
    't
    -0.18
    'm
    -0.18
    POSITIVE LOGITS
     ‘
    0.46
     ’
    0.41
     “
    0.39
    ’
    0.36
    ’s
    0.35
    ’,
    0.34
     (“
    0.33
    ’m
    0.33
    ’d
    0.33
    ’n
    0.32
    Activations Density 0.474%

    No Known Activations