© 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. 46150
    Prev
    Next
    INDEX
    Explanations

    citation markers

    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
     Frag
    -0.09
     Entr
    -0.09
     craving
    -0.09
     tent
    -0.08
     near
    -0.08
    tent
    -0.08
     prom
    -0.08
     Hanson
    -0.08
     Rem
    -0.08
    izz
    -0.08
    POSITIVE LOGITS
     cul
    0.12
    cek
    0.11
    uby
    0.10
    unga
    0.10
     situation
    0.10
    orig
    0.10
    cul
    0.09
     satur
    0.09
    alles
    0.09
    olib
    0.09
    Activations Density 0.073%

    No Known Activations