© 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. 32219
    Prev
    Next
    INDEX
    Explanations

    fits most sizes

    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
     Bord
    -0.09
    Op
    -0.09
     Opportunities
    -0.08
     Borg
    -0.08
     Floor
    -0.08
     Ung
    -0.08
     Ara
    -0.08
     tempting
    -0.08
     seaw
    -0.08
    cn
    -0.08
    POSITIVE LOGITS
     diam
    0.11
     benefici
    0.10
     petite
    0.10
     sensit
    0.10
     (>
    0.10
     fits
    0.10
     modest
    0.09
    -average
    0.09
     enthus
    0.09
     thicker
    0.09
    Activations Density 0.298%

    No Known Activations