© 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. 45952
    Prev
    Next
    INDEX
    Explanations

    view this post or video

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     unp
    -0.10
     Wid
    -0.09
     nearer
    -0.09
    zie
    -0.09
    ropolis
    -0.09
    fur
    -0.09
     brows
    -0.09
     narrow
    -0.08
    Clip
    -0.08
     Easy
    -0.08
    POSITIVE LOGITS
     postfix
    0.10
     Daly
    0.10
     Trib
    0.10
     celebr
    0.10
     linger
    0.10
    -conf
    0.09
    linger
    0.09
     consolid
    0.09
    181
    0.09
    iane
    0.09
    Activations Density 0.001%

    No Known Activations