© 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. 111580
    Prev
    Next
    INDEX
    Explanations

    URLs and web links

    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
    管
    -0.10
    MIT
    -0.09
    ansi
    -0.09
    ctor
    -0.09
    .om
    -0.09
     Bradford
    -0.08
    Friend
    -0.08
     piping
    -0.08
    ctions
    -0.08
    egt
    -0.08
    POSITIVE LOGITS
     Wikipedia
    0.15
     wikipedia
    0.10
     Diss
    0.10
     Wiki
    0.10
    www
    0.09
    .wikipedia
    0.09
     stos
    0.09
    ctxt
    0.09
     repositories
    0.09
     cata
    0.09
    Activations Density 0.007%

    No Known Activations