© 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. 50989
    Prev
    Next
    INDEX
    Explanations

    pricing, matching, guaranteed, offer

    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
    oo
    -0.10
     trans
    -0.10
     Champ
    -0.09
    olest
    -0.09
     hopefully
    -0.08
     preach
    -0.08
     Geoff
    -0.08
     transf
    -0.08
     Kop
    -0.08
     assumptions
    -0.08
    POSITIVE LOGITS
     Abyss
    0.12
     Conc
    0.11
     conc
    0.11
    iente
    0.10
     hut
    0.10
    bane
    0.10
     undercut
    0.10
    @brief
    0.10
     PRICE
    0.09
     hail
    0.09
    Activations Density 0.001%

    No Known Activations