© 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. 117595
    Prev
    Next
    INDEX
    Explanations

    privacy and cookies

    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
    ÌĢ
    -0.10
     Gilles
    -0.10
    ying
    -0.09
     Sticky
    -0.09
    oton
    -0.09
     immortal
    -0.09
    eya
    -0.09
    aml
    -0.09
    {}\
    -0.09
     iy
    -0.09
    POSITIVE LOGITS
     drawback
    0.11
     downside
    0.10
     .↵↵
    0.10
     ...↵↵
    0.10
    however
    0.09
    hawks
    0.09
     .↵
    0.09
     Splash
    0.09
    IDEO
    0.09
     Remed
    0.09
    Activations Density 0.022%

    No Known Activations