© 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. 3623
    Prev
    Next
    INDEX
    Explanations

    firstly, foremost, importantly

    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
     soon
    -0.10
    soon
    -0.10
     dozen
    -0.10
    oj
    -0.09
     Soon
    -0.09
     handful
    -0.09
    oyo
    -0.09
    /result
    -0.09
    /link
    -0.09
     dozens
    -0.09
    POSITIVE LOGITS
     foremost
    0.29
     importantly
    0.17
     paramount
    0.13
    Lastly
    0.12
    imately
    0.12
     firstly
    0.11
     Firstly
    0.11
    uably
    0.10
    ically
    0.10
     primarily
    0.10
    Activations Density 0.012%

    No Known Activations