© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 26872
    Prev
    Next
    INDEX
    Explanations

    staying updated

    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
     specificity
    -0.08
     obstruct
    -0.07
     repeatedly
    -0.07
     precision
    -0.07
     challenging
    -0.07
     discretionary
    -0.07
     frightened
    -0.07
     Grill
    -0.07
     sensitivity
    -0.06
     aided
    -0.06
    POSITIVE LOGITS
     updates
    0.39
     developments
    0.39
     news
    0.37
     Updates
    0.31
     trends
    0.30
    updates
    0.30
     latest
    0.29
    Updates
    0.28
     events
    0.28
    news
    0.26
    Activations Density 0.502%

    No Known Activations