© 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. 27140
    Prev
    Next
    INDEX
    Explanations

    Corporation copyright notices

    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
     postage
    -0.12
     COVID
    -0.08
    COVID
    -0.08
     Freddie
    -0.08
     mot
    -0.08
     spectators
    -0.08
     Maur
    -0.07
     motorists
    -0.07
     audible
    -0.07
     filmed
    -0.07
    POSITIVE LOGITS
     AI
    0.21
    Chat
    0.20
     Chat
    0.19
     Prompt
    0.19
     dalle
    0.19
    AI
    0.19
     prompt
    0.18
    .AI
    0.18
     ai
    0.18
    Prompt
    0.18
    Activations Density 0.122%

    No Known Activations