© 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. 16977
    Prev
    Next
    INDEX
    Explanations

    how something is done

    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
    spiel
    -0.11
    ixe
    -0.11
    ery
    -0.10
    ieber
    -0.10
    ERY
    -0.10
     snug
    -0.10
     Managed
    -0.09
    -minded
    -0.09
    y
    -0.09
    anel
    -0.09
    POSITIVE LOGITS
    oles
    0.11
    isms
    0.10
    cate
    0.10
    ishes
    0.10
    ered
    0.10
     Grinder
    0.09
    ning
    0.09
    forth
    0.09
    ism
    0.09
    ial
    0.09
    Activations Density 0.009%

    No Known Activations