© 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. 14041
    Prev
    Next
    INDEX
    Explanations

    in, on, or amidst

    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
    inton
    -0.12
    endo
    -0.12
     Sab
    -0.12
    enia
    -0.11
    APO
    -0.11
    ertas
    -0.11
    elic
    -0.11
    elen
    -0.11
    UDA
    -0.11
    uce
    -0.11
    POSITIVE LOGITS
     otherwise
    0.60
    otherwise
    0.42
     Otherwise
    0.42
     amidst
    0.40
    Otherwise
    0.40
     amid
    0.36
     OTHERWISE
    0.30
     Amid
    0.29
     midst
    0.27
    åIJ¦
    0.27
    Activations Density 0.253%

    No Known Activations