© 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. 48309
    Prev
    Next
    INDEX
    Explanations

    heard about something

    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
    azen
    -0.12
     visible
    -0.11
     foreseeable
    -0.11
     Memories
    -0.10
     visibly
    -0.10
    iot
    -0.10
     recognizable
    -0.10
     observable
    -0.09
    .Imaging
    -0.09
     Marketable
    -0.09
    POSITIVE LOGITS
     vaguely
    0.13
     hears
    0.12
     heard
    0.10
     firsthand
    0.10
     hear
    0.10
     tid
    0.09
     vague
    0.09
     hearing
    0.09
     Leaf
    0.09
     Hearing
    0.09
    Activations Density 0.092%

    No Known Activations