© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 34158
    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
    Negative Logits
     Jacobs
    -0.10
     DJs
    -0.10
    rena
    -0.10
     Gord
    -0.09
    ój
    -0.09
    uti
    -0.09
    ombies
    -0.09
    allon
    -0.09
    ót
    -0.08
     Nelson
    -0.08
    POSITIVE LOGITS
     Means
    0.10
     surprise
    0.10
     means
    0.09
     Assigned
    0.09
    SU
    0.09
     Surprise
    0.09
     Magnum
    0.09
     delights
    0.08
    rett
    0.08
     Eld
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.