© 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. 48481
    Prev
    Next
    INDEX
    Explanations

    you need / you have

    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
     surely
    -0.16
     obviously
    -0.15
     hopefully
    -0.13
     certainly
    -0.13
     apparently
    -0.11
     slate
    -0.10
     admittedly
    -0.10
     actually
    -0.10
     truly
    -0.10
     guaranteed
    -0.10
    POSITIVE LOGITS
     adequate
    0.11
    shan
    0.11
     Vaults
    0.10
    orgot
    0.10
     adequ
    0.10
    Fin
    0.10
    ADE
    0.10
     adequately
    0.10
     Fin
    0.10
     confort
    0.10
    Activations Density 0.004%

    No Known Activations