© 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. 4979
    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
     substant
    -0.09
    .native
    -0.08
     envis
    -0.08
    alis
    -0.08
     Industry
    -0.08
    uria
    -0.08
    asil
    -0.08
     genu
    -0.08
     salvage
    -0.08
     industry
    -0.08
    POSITIVE LOGITS
     boo
    0.10
     Boone
    0.09
     heel
    0.09
    reh
    0.09
    utherford
    0.09
    DET
    0.09
     granny
    0.09
    PB
    0.09
     Roberts
    0.09
     Cir
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.