© 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. 28298
    Prev
    Next
    INDEX
    Explanations

    academic conferences, complexity, detail, keyword, commentary, low-level

    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
    hb
    -0.10
     Gat
    -0.10
     tram
    -0.10
     inscription
    -0.10
     disclaimer
    -0.09
     Huffman
    -0.09
     Pemb
    -0.09
     Dere
    -0.09
    
    -0.09
     dors
    -0.09
    POSITIVE LOGITS
     readability
    0.11
     persu
    0.10
     target
    0.10
     conc
    0.10
    SELL
    0.09
     outr
    0.09
     Audience
    0.08
     konk
    0.08
    coh
    0.08
     lust
    0.08
    Activations Density 0.008%

    No Known Activations