© 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. 15597
    Prev
    Next
    INDEX
    Explanations

    had no idea that

    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
     evidently
    -0.16
     presumably
    -0.15
     seems
    -0.14
     seem
    -0.14
     apparently
    -0.13
     hopefully
    -0.13
     obviously
    -0.13
     seemed
    -0.12
     must
    -0.12
     somehow
    -0.12
    POSITIVE LOGITS
     already
    0.15
     Already
    0.14
    å·²
    0.12
     secretly
    0.12
    already
    0.11
     harb
    0.10
     concurrently
    0.10
    Already
    0.10
     quietly
    0.10
     simultaneously
    0.10
    Activations Density 0.081%

    No Known Activations