© 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. 32313
    Prev
    Next
    INDEX
    Explanations

    and or related to lists

    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
    ter
    -0.07
     slapped
    -0.07
    orie
    -0.07
    ONUS
    -0.07
     Commerce
    -0.07
     Mirror
    -0.07
    069
    -0.07
    azon
    -0.07
     sucker
    -0.07
    ora
    -0.07
    POSITIVE LOGITS
     yourselves
    0.11
    itorio
    0.10
     unt
    0.10
     Sesso
    0.10
     motto
    0.10
    addock
    0.10
    /request
    0.10
     unh
    0.10
     Hoe
    0.10
    .Companion
    0.10
    Activations Density 0.033%

    No Known Activations