© 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. 30909
    Prev
    Next
    INDEX
    Explanations

    every day or year counts

    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
     Genetics
    -0.09
    еÑģÑĮ
    -0.08
    jit
    -0.08
     exposition
    -0.08
     Huss
    -0.08
     Hispan
    -0.08
     Sang
    -0.08
     Mare
    -0.08
     stint
    -0.08
     Gu
    -0.08
    POSITIVE LOGITS
     millions
    0.25
     thousands
    0.23
     billions
    0.23
     Thousands
    0.20
     somewhere
    0.20
     Millions
    0.18
     countless
    0.18
     tens
    0.17
    Thousands
    0.16
     hundreds
    0.16
    Activations Density 0.477%

    No Known Activations