© 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. 88372
    Prev
    Next
    INDEX
    Explanations

    contestant/nominee/competitor

    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
    ago
    -0.12
     staffers
    -0.11
     ostensibly
    -0.11
     abound
    -0.11
     erst
    -0.10
    arde
    -0.10
     seeming
    -0.10
     bits
    -0.10
     sembl
    -0.10
     darn
    -0.10
    POSITIVE LOGITS
     firstly
    0.10
     tod
    0.09
     burdens
    0.09
     Moh
    0.09
     vigorously
    0.09
    ului
    0.08
     prov
    0.08
     fundament
    0.08
     achie
    0.08
     enormously
    0.08
    Activations Density 0.112%

    No Known Activations