© 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. 113237
    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
     staffers
    -0.09
    ago
    -0.08
    IOD
    -0.08
     eng
    -0.08
     grind
    -0.08
     Sen
    -0.08
    "]];↵
    -0.08
     Woodward
    -0.08
     Vick
    -0.08
     seniors
    -0.08
    POSITIVE LOGITS
     Floyd
    0.10
     theoretically
    0.10
    Callbacks
    0.10
    emu
    0.09
    rale
    0.09
     depr
    0.09
    akk
    0.09
     Fet
    0.09
    OnClick
    0.09
    ngen
    0.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.