© 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. 14734
    Prev
    Next
    INDEX
    Explanations

    seek to understand

    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
     optimum
    -0.11
     thru
    -0.11
     indef
    -0.11
     bogus
    -0.11
     Fri
    -0.11
     Instit
    -0.10
     stint
    -0.10
     insure
    -0.10
     terribly
    -0.10
     impres
    -0.10
    POSITIVE LOGITS
     personalized
    0.11
     transformative
    0.09
     customized
    0.09
     customization
    0.09
     aligned
    0.09
     captivating
    0.09
     exploration
    0.09
     individuals
    0.09
     align
    0.09
     wishlist
    0.09
    Activations Density 0.312%

    No Known Activations