© 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. 6164
    Prev
    Next
    INDEX
    Explanations

    Arbuthnot, Lockett, monolog, 819, Dalaca, Sanderling

    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
    cae
    -0.09
    ying
    -0.08
    zin
    -0.08
    .named
    -0.08
    dae
    -0.08
    anten
    -0.07
     quietly
    -0.07
    configs
    -0.07
     locals
    -0.07
     gn
    -0.07
    POSITIVE LOGITS
     pcl
    0.12
    à¹Į
    0.11
     breat
    0.10
     occas
    0.10
    blick
    0.10
     Moody
    0.10
     intox
    0.09
    apiro
    0.09
     haber
    0.09
     radically
    0.09
    Activations Density 0.104%

    No Known Activations