© 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. 8024
    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
    gon
    -0.10
     mus
    -0.10
     Presidents
    -0.09
     invites
    -0.09
    iore
    -0.09
    -exc
    -0.09
     Abel
    -0.09
     Patch
    -0.09
    @stop
    -0.09
     exciting
    -0.09
    POSITIVE LOGITS
     earm
    0.10
    otts
    0.09
     Consent
    0.09
    itta
    0.09
     flea
    0.09
    adas
    0.09
     comprom
    0.08
    igmat
    0.08
     subst
    0.08
     rebound
    0.08
    Activations Density 0.000%

    No Known Activations