© 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. 33879
    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
     Freddie
    -0.09
     pony
    -0.08
    adm
    -0.08
     buff
    -0.08
     pon
    -0.07
     plush
    -0.07
     Pike
    -0.07
     generously
    -0.07
    /network
    -0.07
    emed
    -0.07
    POSITIVE LOGITS
     Burst
    0.12
    æij
    0.11
     Hak
    0.11
    /Dk
    0.11
     burst
    0.11
    _OW
    0.10
    osi
    0.10
    astes
    0.10
    Īëĭ¤
    0.10
     Reco
    0.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.