© 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. 5825
    Prev
    Next
    INDEX
    Explanations

    company

    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
    bia
    -0.10
     existence
    -0.10
    ondo
    -0.10
     panc
    -0.09
     interconnected
    -0.09
     coordinated
    -0.09
    subj
    -0.09
    essa
    -0.09
    alous
    -0.09
    isko
    -0.09
    POSITIVE LOGITS
     company
    0.18
    company
    0.17
     Company
    0.15
     companions
    0.14
    Company
    0.14
     COMPANY
    0.13
    -company
    0.12
     compan
    0.12
    (company
    0.12
     companies
    0.12
    Activations Density 0.013%

    No Known Activations