© 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. 17976
    Prev
    Next
    INDEX
    Explanations

    exposure, deletion, LP, images, marriage

    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
     previously
    -0.11
     anymore
    -0.10
     risen
    -0.10
     recently
    -0.09
     embroid
    -0.09
    sel
    -0.09
    805
    -0.08
     beaten
    -0.08
     lately
    -0.08
    handles
    -0.08
    POSITIVE LOGITS
     quickly
    0.18
     instantly
    0.16
     immediately
    0.15
     surprisingly
    0.14
     surprised
    0.13
     unsur
    0.13
     proved
    0.13
     initially
    0.13
     promptly
    0.13
    Immediately
    0.13
    Activations Density 0.072%

    No Known Activations