© 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. 33956
    Prev
    Next
    INDEX
    Explanations

    admitting embarrassment or shame

    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
     democr
    -0.10
     obedient
    -0.09
     exc
    -0.09
    Bookmark
    -0.09
    ien
    -0.09
     plat
    -0.09
    itel
    -0.09
     gesch
    -0.09
    ibi
    -0.09
    ulan
    -0.09
    POSITIVE LOGITS
     lest
    0.12
     admitting
    0.11
    /dist
    0.11
     Ack
    0.11
     touching
    0.11
     even
    0.10
     acknowledging
    0.10
    /un
    0.10
     admit
    0.09
     acknow
    0.09
    Activations Density 0.025%

    No Known Activations