© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 90897
    Prev
    Next
    INDEX
    Explanations

    `.com` and `ECT`

    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
    :</
    -0.10
    nder
    -0.10
    —including
    -0.10
    !),
    -0.10
    !)
    -0.10
    :&
    -0.10
     &↵
    -0.10
    !).↵↵
    -0.09
    <tbody
    -0.09
    <tr
    -0.09
    POSITIVE LOGITS
    ↵↵
    0.16
    <|endoftext|>
    0.11
    ,},↵
    0.11
    ↵↵↵
    0.11
     |↵↵
    0.10
      ↵↵
    0.10
    "],"
    0.10
    ↵
    0.10
     ]↵↵
    0.10
    .↵↵
    0.09
    Activations Density 1.149%

    No Known Activations