© 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. 114524
    Prev
    Next
    INDEX
    Explanations

    services and offerings

    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
     imper
    -0.10
     patents
    -0.09
     cookbook
    -0.09
     insurers
    -0.09
     classifiers
    -0.09
     Prairie
    -0.09
    162
    -0.09
    AccessToken
    -0.09
     planner
    -0.09
     karma
    -0.09
    POSITIVE LOGITS
     services
    0.54
    services
    0.40
     service
    0.38
     Services
    0.38
     SERVICES
    0.32
    -services
    0.32
    æľįåĬ¡
    0.32
    Services
    0.31
    _services
    0.30
     servicios
    0.26
    Activations Density 0.453%

    No Known Activations