© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117378
    Prev
    Next
    INDEX
    Explanations

    I or we followed by past action 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
    Negative Logits
     recent
    -0.18
     recently
    -0.17
     later
    -0.16
    recent
    -0.15
     continued
    -0.14
     Recently
    -0.13
     lately
    -0.13
     subsequently
    -0.13
    later
    -0.13
    _recent
    -0.12
    POSITIVE LOGITS
     briefly
    0.16
     promised
    0.12
     mistakenly
    0.11
     temporarily
    0.11
    `.`
    0.11
     vowed
    0.10
    survey
    0.10
    izio
    0.10
     Morrow
    0.10
    prit
    0.10
    Activations Density 0.254%

    No Known Activations