© 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. 7895
    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
     Relationship
    -0.09
     vanity
    -0.09
     cree
    -0.09
     twee
    -0.09
    alk
    -0.09
    -meta
    -0.08
    ocr
    -0.08
    anka
    -0.08
    eto
    -0.08
    atio
    -0.08
    POSITIVE LOGITS
     transfers
    0.26
     transfer
    0.25
     exchanged
    0.24
     exchanging
    0.24
     transferring
    0.24
     exchanges
    0.24
     exchange
    0.23
     Transfer
    0.22
     passing
    0.21
     transferred
    0.21
    Activations Density 0.339%

    No Known Activations