© 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. 111545
    Prev
    Next
    INDEX
    Explanations

    cornered, hunted, driven

    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
     Foley
    -0.11
     reordered
    -0.11
    ena
    -0.11
    ury
    -0.11
     Marino
    -0.10
    ENA
    -0.10
    sid
    -0.10
    utos
    -0.10
     blurred
    -0.10
    entar
    -0.09
    POSITIVE LOGITS
     corner
    0.28
     Corner
    0.23
    Corner
    0.21
    corner
    0.19
     trapped
    0.17
    -corner
    0.17
     corners
    0.17
     forced
    0.15
     forcing
    0.15
     flushing
    0.14
    Activations Density 0.074%

    No Known Activations