© 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. 46299
    Prev
    Next
    INDEX
    Explanations

    biography, description, history

    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
     Carson
    -0.10
     fab
    -0.10
     Gunn
    -0.09
     Ling
    -0.09
     Ingen
    -0.08
     tantal
    -0.08
     jack
    -0.08
     atheist
    -0.08
    .El
    -0.08
    fab
    -0.08
    POSITIVE LOGITS
     hardened
    0.13
     dashed
    0.10
     Industrial
    0.10
     cr
    0.09
     dash
    0.09
    ÑĮÑİ
    0.09
     oppos
    0.09
     rem
    0.09
    +_
    0.09
     median
    0.09
    Activations Density 0.008%

    No Known Activations