© 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. 50723
    Prev
    Next
    INDEX
    Explanations

    ways to get something done

    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
     Khal
    -0.10
    crawl
    -0.10
     Hak
    -0.10
     swagger
    -0.10
    mind
    -0.09
    tte
    -0.09
    grp
    -0.09
    ëĵ
    -0.09
    lyn
    -0.09
     parity
    -0.09
    POSITIVE LOGITS
    oints
    0.09
    ema
    0.09
     tamp
    0.09
    ä¾Ľ
    0.09
     impres
    0.09
     tit
    0.09
    nda
    0.09
    aida
    0.08
     effort
    0.08
    cent
    0.08
    Activations Density 0.004%

    No Known Activations