© 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. 46246
    Prev
    Next
    INDEX
    Explanations

    based; -centric

    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
     Laurent
    -0.08
     evapor
    -0.08
     Blitz
    -0.08
     stalk
    -0.08
    ilos
    -0.08
    734
    -0.08
    JB
    -0.07
    IAM
    -0.07
    oad
    -0.07
     intrigue
    -0.07
    POSITIVE LOGITS
    -based
    0.22
    -centric
    0.17
    -Based
    0.17
    -dominated
    0.13
     alone
    0.13
     Alone
    0.12
    -type
    0.12
     traditional
    0.12
    /core
    0.12
    -centered
    0.12
    Activations Density 0.144%

    No Known Activations