© 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. 5228
    Prev
    Next
    INDEX
    Explanations

    participants and subjects

    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
    visible
    -0.09
     tonight
    -0.09
     elsewhere
    -0.09
    Books
    -0.09
     upcoming
    -0.09
     mort
    -0.09
    paralle
    -0.09
     lately
    -0.09
     pitch
    -0.08
     Tent
    -0.08
    POSITIVE LOGITS
     participants
    0.41
     Participants
    0.35
     participant
    0.33
    Participants
    0.31
     respondents
    0.31
    participants
    0.30
     subjects
    0.30
     study
    0.29
     Participant
    0.29
     Subjects
    0.28
    Activations Density 2.668%

    No Known Activations