© 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. 15588
    Prev
    Next
    INDEX
    Explanations

    gas powered, CA Oradea, Malaysian Qualifications

    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
     prof
    -0.09
     weblog
    -0.09
     Occupy
    -0.09
     Indies
    -0.08
     UNU
    -0.08
     Zap
    -0.08
     Ire
    -0.08
     Checkout
    -0.08
     newcomer
    -0.08
     Gecko
    -0.08
    POSITIVE LOGITS
     hairstyles
    0.13
     meaning
    0.12
     hairstyle
    0.11
     meanings
    0.11
    foods
    0.11
    sitemap
    0.11
     haircut
    0.11
     lyrics
    0.10
     Stevens
    0.10
     abbrev
    0.10
    Activations Density 0.119%

    No Known Activations