© 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. 14089
    Prev
    Next
    INDEX
    Explanations

    I followed by verb

    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
     simply
    -0.10
     expl
    -0.09
    pig
    -0.09
     darm
    -0.09
    /high
    -0.09
    uni
    -0.09
     relating
    -0.09
    BOOLEAN
    -0.09
     paper
    -0.09
    olated
    -0.09
    POSITIVE LOGITS
     outward
    0.13
     dearly
    0.11
     KNOW
    0.11
     love
    0.11
     dislike
    0.11
     knew
    0.10
     lack
    0.10
     know
    0.10
    know
    0.10
     doubts
    0.10
    Activations Density 0.031%

    No Known Activations