© 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. 113547
    Prev
    Next
    INDEX
    Explanations

    companies hiring or seeking

    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
     Purchase
    -0.11
     unc
    -0.10
     encount
    -0.10
    segue
    -0.10
     Fut
    -0.10
    "go
    -0.10
     Elias
    -0.09
     Stan
    -0.09
     Purch
    -0.09
     transports
    -0.09
    POSITIVE LOGITS
     waiting
    0.20
     ready
    0.20
     eager
    0.18
     listed
    0.17
     willing
    0.17
     awaiting
    0.17
     WANT
    0.16
     actively
    0.16
     wanting
    0.16
    waiting
    0.15
    Activations Density 0.032%

    No Known Activations