© 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. 117382
    Prev
    Next
    INDEX
    Explanations

    code includes and acknowledgments

    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
     Blitz
    -0.09
     Ashton
    -0.09
     Ding
    -0.09
    una
    -0.09
     Sabha
    -0.08
     Fen
    -0.08
     peg
    -0.08
    ç¼
    -0.08
     outward
    -0.08
    Chess
    -0.08
    POSITIVE LOGITS
     Needless
    0.12
    ･･
    0.12
    ãģĤãĤĬãģĮ
    0.11
    sei
    0.10
     Wak
    0.10
     plur
    0.10
    ãĥ»ãĥ»
    0.10
    ï¼Ī
    0.10
    amura
    0.10
    -san
    0.10
    Activations Density 0.003%

    No Known Activations