© 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. 116142
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     guid
    -0.11
    odox
    -0.08
    oped
    -0.08
    ãĢĤ↵↵↵↵↵↵
    -0.08
     Dale
    -0.08
    ares
    -0.08
     Ventures
    -0.08
    zend
    -0.08
    vez
    -0.08
    bai
    -0.08
    POSITIVE LOGITS
    iar
    0.11
     punches
    0.10
     blocking
    0.10
     Wat
    0.10
     Ung
    0.10
     rais
    0.10
     separ
    0.09
    cription
    0.09
    emma
    0.09
     Hum
    0.09
    Activations Density 0.000%

    No Known Activations