© 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. 34099
    Prev
    Next
    INDEX
    Explanations

    many people want or prefer

    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
     probably
    -0.12
     yourselves
    -0.11
     behaved
    -0.10
     hopefully
    -0.10
     your
    -0.10
    ment
    -0.10
     Probably
    -0.10
     bem
    -0.09
     yourself
    -0.09
    Walk
    -0.09
    POSITIVE LOGITS
     prefer
    0.18
     liken
    0.15
     swear
    0.13
     prefers
    0.11
     Prefer
    0.11
     mistakenly
    0.11
     preferring
    0.11
     Dys
    0.10
     choose
    0.10
     understandably
    0.10
    Activations Density 0.043%

    No Known Activations