© 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. 14971
    Prev
    Next
    INDEX
    Explanations

    industry and community practitioners

    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
     societal
    -0.15
     household
    -0.12
     Household
    -0.12
     childhood
    -0.12
     parental
    -0.12
     citizens
    -0.11
     Parent
    -0.11
     millions
    -0.11
     Citizens
    -0.11
     Millions
    -0.11
    POSITIVE LOGITS
     community
    0.19
     industry
    0.18
     practitioners
    0.18
    -community
    0.17
     newcomers
    0.17
    industry
    0.17
    community
    0.16
     veteran
    0.16
    Community
    0.16
     Community
    0.15
    Activations Density 0.934%

    No Known Activations