© 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. 28545
    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
     reaction
    -0.10
    ensch
    -0.10
     em
    -0.09
     Merchant
    -0.09
    po
    -0.09
     Cunning
    -0.09
    orthy
    -0.09
    dismiss
    -0.09
     refinement
    -0.09
     Gloss
    -0.09
    POSITIVE LOGITS
     despair
    0.09
    Destructor
    0.09
     propag
    0.09
     unsett
    0.08
     miserable
    0.08
     rz
    0.08
    -bin
    0.08
     hardship
    0.08
     serial
    0.08
     Gregg
    0.08
    Activations Density 0.000%

    No Known Activations