© 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. 27756
    Prev
    Next
    INDEX
    Explanations

    offering services or advice

    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
     grouping
    -0.10
     amph
    -0.10
    ë²Ħ
    -0.10
     bald
    -0.09
    .EventQueue
    -0.09
     Tro
    -0.09
    ogl
    -0.09
     equip
    -0.09
     Produced
    -0.09
    engine
    -0.09
    POSITIVE LOGITS
     services
    0.20
    services
    0.17
     advice
    0.17
     assistance
    0.16
     Services
    0.13
     Advice
    0.13
     guidance
    0.13
     entertainment
    0.13
     service
    0.12
    Services
    0.12
    Activations Density 0.039%

    No Known Activations