© 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. 29491
    Prev
    Next
    INDEX
    Explanations

    reading opinions and reviews

    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
    Not in Any Lists

    No Comments

    Negative Logits
    IPP
    -0.12
    -bg
    -0.12
     stamped
    -0.12
     silently
    -0.12
     Cooperation
    -0.12
    UIS
    -0.11
     periodically
    -0.11
     leisure
    -0.11
    elib
    -0.11
     Unused
    -0.11
    POSITIVE LOGITS
     consensus
    0.13
     convinced
    0.12
     conflicting
    0.11
     decided
    0.11
     hype
    0.11
     deciding
    0.11
     glowing
    0.10
     persuaded
    0.10
     heard
    0.10
     reviewers
    0.10
    Activations Density 0.359%

    No Known Activations