© 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. 5248
    Prev
    Next
    INDEX
    Explanations

    release of public information or chemical substances

    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
     takeaway
    -0.09
     icing
    -0.09
     Provid
    -0.09
     Sund
    -0.09
    berman
    -0.08
    nia
    -0.08
     sund
    -0.08
     Vernon
    -0.08
    THR
    -0.08
    astro
    -0.08
    POSITIVE LOGITS
     tension
    0.19
     tensions
    0.19
     trapped
    0.15
     pent
    0.15
     stored
    0.15
     imprisoned
    0.15
     hostages
    0.14
     latent
    0.13
     pressure
    0.13
     secrets
    0.13
    Activations Density 0.105%

    No Known Activations