© 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. 117321
    Prev
    Next
    INDEX
    Explanations

    the fact that

    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
     hopefully
    -0.14
     Hopefully
    -0.12
    Hopefully
    -0.12
     sufficient
    -0.11
    allet
    -0.11
     simplicity
    -0.10
    illard
    -0.10
     enough
    -0.10
    allee
    -0.10
     hoped
    -0.10
    POSITIVE LOGITS
     coinc
    0.11
     backdrop
    0.10
     visibly
    0.10
     meanwhile
    0.09
    fact
    0.09
    onis
    0.09
     practically
    0.09
     whenever
    0.09
     unknow
    0.09
     everytime
    0.09
    Activations Density 0.047%

    No Known Activations