© 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. 111621
    Prev
    Next
    INDEX
    Explanations

    seeking someone or something suitable

    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
     unintended
    -0.09
     impress
    -0.08
    ubo
    -0.08
     Lever
    -0.08
     impression
    -0.08
    anto
    -0.08
    etti
    -0.08
     award
    -0.08
     Fate
    -0.08
    019
    -0.08
    POSITIVE LOGITS
     whom
    0.18
     preferably
    0.18
     willing
    0.18
     reliably
    0.16
     recip
    0.16
     compatible
    0.15
     understands
    0.15
     capable
    0.14
    who
    0.14
     who
    0.14
    Activations Density 0.054%

    No Known Activations