© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31944
    Prev
    Next
    INDEX
    Explanations

    official capacity

    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
     Mug
    -0.09
     reactions
    -0.09
     prospects
    -0.09
     rarely
    -0.09
    emm
    -0.09
    (KP
    -0.09
     Coff
    -0.09
    oom
    -0.09
     plat
    -0.09
     upbeat
    -0.09
    POSITIVE LOGITS
     entrusted
    0.16
     technically
    0.15
     sovereign
    0.14
     contractual
    0.14
     legally
    0.14
     contract
    0.13
     formally
    0.13
     authority
    0.13
     officially
    0.13
     contracted
    0.12
    Activations Density 0.198%

    No Known Activations