© 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. 31528
    Prev
    Next
    INDEX
    Explanations

    end of section or thought

    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
     furthermore
    -0.14
     moreover
    -0.12
     additionally
    -0.12
     Later
    -0.12
     myself
    -0.11
     subsequently
    -0.10
     Elli
    -0.10
     Anyway
    -0.10
     leash
    -0.10
     provisioning
    -0.10
    POSITIVE LOGITS
    Sometimes
    0.10
    {*
    0.09
    This
    0.09
    Imagine
    0.08
     traditionally
    0.08
    بر
    0.08
    ↵↵↵↵↵↵↵
    0.08
    —a
    0.08
     zwar
    0.08
     endregion
    0.08
    Activations Density 0.136%

    No Known Activations