© 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. 34237
    Prev
    Next
    INDEX
    Explanations

    one in number

    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
    oes
    -0.12
    leton
    -0.10
    aggi
    -0.10
    erosis
    -0.10
     fest
    -0.10
    rama
    -0.10
    gba
    -0.09
    -times
    -0.09
    oft
    -0.09
    ikes
    -0.09
    POSITIVE LOGITS
     every
    0.16
    _every
    0.12
     Every
    0.12
    Every
    0.12
    .every
    0.11
    every
    0.11
     Norris
    0.10
     four
    0.09
     Bert
    0.09
     tenth
    0.09
    Activations Density 0.146%

    No Known Activations