© 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. 50431
    Prev
    Next
    INDEX
    Explanations

    parts meanings significance genesis origin

    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
     idea
    -0.11
     abilities
    -0.10
     ideas
    -0.10
     experiences
    -0.09
    idea
    -0.09
     discontinued
    -0.09
     knowledge
    -0.09
     expertise
    -0.09
     talents
    -0.09
     attitudes
    -0.08
    POSITIVE LOGITS
     roots
    0.19
     implications
    0.19
     relevance
    0.19
     meaning
    0.18
     significance
    0.18
     ramifications
    0.18
     implication
    0.16
     counterparts
    0.16
     importance
    0.15
     repercussions
    0.15
    Activations Density 0.328%

    No Known Activations