© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32910
    Prev
    Next
    INDEX
    Explanations

    frequency per day

    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
     periodically
    -0.15
     periodic
    -0.13
     occasional
    -0.12
     regularly
    -0.12
     recurring
    -0.11
     years
    -0.11
     prolong
    -0.10
     repeated
    -0.10
     occasionally
    -0.10
     Annual
    -0.10
    POSITIVE LOGITS
     twice
    0.13
     Twice
    0.13
     once
    0.10
     Afr
    0.10
    tw
    0.10
     every
    0.10
    every
    0.10
     Every
    0.10
    once
    0.10
    apon
    0.09
    Activations Density 0.150%

    No Known Activations