© 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. 15553
    Prev
    Next
    INDEX
    Explanations

    getting deeper, smaller, cheaper, less, more, stronger

    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
     recon
    -0.08
     unprotected
    -0.08
    ortal
    -0.08
     Holl
    -0.08
     grieving
    -0.08
     Trev
    -0.08
     thinly
    -0.08
    ron
    -0.08
    ehler
    -0.08
    orio
    -0.07
    POSITIVE LOGITS
     easier
    0.19
     harder
    0.18
     stronger
    0.17
     worse
    0.17
     richer
    0.16
     quieter
    0.16
     hotter
    0.16
     simpler
    0.16
     weaker
    0.16
     happier
    0.16
    Activations Density 0.101%

    No Known Activations