© 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. 25297
    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
     tent
    -0.12
     Tower
    -0.11
     simult
    -0.10
    engo
    -0.10
     towers
    -0.10
    tent
    -0.10
    otron
    -0.10
     Pars
    -0.10
     Towers
    -0.09
     tents
    -0.09
    POSITIVE LOGITS
     ADA
    0.10
     carr
    0.09
    rss
    0.09
    /gallery
    0.09
     Hang
    0.09
     TAS
    0.09
     Quarter
    0.08
     Cur
    0.08
     nep
    0.08
    UST
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.