© 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. 116110
    Prev
    Next
    INDEX
    Explanations

    code structure markers

    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
    Âł↵
    -0.12
        ↵
    -0.12
    &nbsp
    -0.12
       ↵
    -0.11
      ↵
    -0.11
    ³³
    -0.11
    \↵
    -0.11
    Âł
    -0.11
    ³³³
    -0.10
    ↵
    -0.10
    POSITIVE LOGITS
     âĢ¢
    0.23
    âĢ¢
    0.15
    .âĢ¢
    0.14
     |--------------------------------------------------------------------------↵
    0.13
     ![
    0.12
     ```↵
    0.12
     ...↵↵↵↵
    0.11
     http
    0.11
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.11
    ngo
    0.10
    Activations Density 0.693%

    No Known Activations