© 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. 4887
    Prev
    Next
    INDEX
    Explanations

    research and gathering information

    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
     guessing
    -0.11
     Guess
    -0.09
     remembering
    -0.09
     numbered
    -0.09
     Observation
    -0.09
     Memories
    -0.09
     guessed
    -0.09
     gently
    -0.09
     detections
    -0.08
    Observ
    -0.08
    POSITIVE LOGITS
     researching
    0.52
     researched
    0.51
     research
    0.45
    research
    0.38
     Research
    0.35
    Research
    0.35
     studying
    0.29
     studied
    0.26
     investigating
    0.26
     reading
    0.25
    Activations Density 0.601%

    No Known Activations