© 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. 16233
    Prev
    Next
    INDEX
    Explanations

    they followed by 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
    was
    -0.13
    ned
    -0.09
     am
    -0.09
     shaken
    -0.09
     blown
    -0.08
     myself
    -0.08
     beaten
    -0.08
     Was
    -0.08
    á»ĩ
    -0.08
    Was
    -0.08
    POSITIVE LOGITS
    're
    0.34
    ’re
    0.32
    /we
    0.24
    re
    0.23
    've
    0.22
    'll
    0.21
    ’ve
    0.21
    ’ll
    0.20
     are
    0.20
    /she
    0.18
    Activations Density 0.115%

    No Known Activations