© 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. 50919
    Prev
    Next
    INDEX
    Explanations

    third-party projects

    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
     presumably
    -0.16
     somehow
    -0.15
     either
    -0.14
     atleast
    -0.12
    oft
    -0.12
    (or
    -0.12
     or
    -0.12
     surely
    -0.12
     irgend
    -0.12
     etwa
    -0.11
    POSITIVE LOGITS
     unrelated
    0.17
     certain
    0.13
     elsewhere
    0.13
     very
    0.12
     Certain
    0.12
    Certain
    0.12
     overseas
    0.11
     abroad
    0.11
     VERY
    0.10
     unexpectedly
    0.10
    Activations Density 2.449%

    No Known Activations