© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 14952
    Prev
    Next
    INDEX
    Explanations

    contribution or addition

    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
     undergo
    -0.10
     anecd
    -0.10
    ddd
    -0.10
     Hastings
    -0.10
     reminis
    -0.10
     romant
    -0.10
     honesty
    -0.10
    ecd
    -0.10
    oso
    -0.10
     testimonials
    -0.10
    POSITIVE LOGITS
     contributions
    0.16
     continuation
    0.15
     additions
    0.15
     contribution
    0.14
     contributors
    0.13
     Contributions
    0.13
     continuity
    0.13
     contributing
    0.12
     collaborators
    0.12
     contributor
    0.12
    Activations Density 0.184%

    No Known Activations