© 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. 116218
    Prev
    Next
    INDEX
    Explanations

    dates and years

    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
    esc
    -0.08
    irma
    -0.08
     shaving
    -0.08
    Escort
    -0.08
    lij
    -0.08
    unger
    -0.08
     Freed
    -0.07
    rush
    -0.07
     orderly
    -0.07
     shave
    -0.07
    POSITIVE LOGITS
     hindsight
    0.10
     Cree
    0.10
     spl
    0.10
     Rou
    0.10
     Conversation
    0.09
     assh
    0.09
    gc
    0.09
    ernel
    0.09
     critically
    0.09
     stro
    0.09
    Activations Density 0.004%

    No Known Activations