© 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. 87989
    Prev
    Next
    INDEX
    Explanations

    point or stage where

    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
    Not in Any Lists

    No Comments

    Negative Logits
    /cop
    -0.11
     Balt
    -0.11
    imore
    -0.10
    ி
    -0.10
     Tod
    -0.10
    gle
    -0.10
     frac
    -0.10
     seal
    -0.10
    ffa
    -0.09
    urma
    -0.09
    POSITIVE LOGITS
     stage
    0.26
     point
    0.24
     where
    0.20
     whereby
    0.18
    stage
    0.18
     situation
    0.16
     Stage
    0.16
     stages
    0.15
    -point
    0.15
    -stage
    0.15
    Activations Density 0.117%

    No Known Activations