© 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. 6837
    Prev
    Next
    INDEX
    Explanations

    visible, openly, publicly

    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
     elusive
    -0.09
     silky
    -0.08
     indirect
    -0.08
     hypothetical
    -0.08
     typename
    -0.08
     cautioned
    -0.07
     taper
    -0.07
    ilton
    -0.07
     hypnot
    -0.07
     lesser
    -0.07
    POSITIVE LOGITS
     visible
    0.66
     openly
    0.57
     publicly
    0.57
     Visible
    0.56
     visibly
    0.50
    visible
    0.49
    -visible
    0.48
    Visible
    0.47
     visibility
    0.46
     Visibility
    0.41
    Activations Density 0.794%

    No Known Activations