© 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. 88480
    Prev
    Next
    INDEX
    Explanations

    defining, quantifying, characterizing, understanding

    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
     Democr
    -0.12
    wat
    -0.12
    (the
    -0.11
     errs
    -0.11
     nir
    -0.10
    zee
    -0.10
    Infos
    -0.10
    -background
    -0.10
     Acres
    -0.10
     Burton
    -0.10
    POSITIVE LOGITS
     and
    0.19
     or
    0.13
     how
    0.12
    并
    0.11
    —and
    0.11
    ãĢģ
    0.10
    	and
    0.10
    /re
    0.09
    /man
    0.09
     key
    0.09
    Activations Density 1.282%

    No Known Activations